Merge tag 'drm-intel-next-fixes-2015-10-22' of git://anongit.freedesktop.org/drm-intel into drm-next

Bunch of -fixes for 4.4. Well not just, I've left the mmio/register work from Ville in here since it's low-risk but lots of churn all over. * tag 'drm-intel-next-fixes-2015-10-22' of git://anongit.freedesktop.org/drm-intel: (23 commits) drm/i915: Use round to closest when computing the CEA 1.001 pixel clocks drm/i915: Kill the leftover RMW from ivb_sprite_disable() drm/i915: restore ggtt double-bind avoidance drm/i915/skl: Enable pipe gamma for sprite planes. drm/i915/skl+: Enable pipe CSC on cursor planes. (v2) MAINTAINERS: add link to the Intel Graphics for Linux web site drm/i915: Move skl/bxt gt specific workarounds to ring init drm/i915: Drop i915_gem_obj_is_pinned() from set-cache-level drm/i915: revert a few more watermark commits drm/i915: Remove dev_priv argument from NEEDS_FORCE_WAKE drm/i915: Clean up LVDS register handling drm/i915: Throw out some useless variables drm/i915: Parametrize and fix SWF registers drm/i915: s/PIPE_FRMCOUNT_GM45/PIPE_FRMCOUNT_G4X/ etc. drm/i915: Turn GEN5_ASSERT_IIR_IS_ZERO() into a function drm/i915: Fix a few bad hex numbers in register defines drm/i915: Protect register macro arguments drm/i915: Include gpio_mmio_base in GMBUS reg defines drm/i915: Parametrize HSW video DIP data registers drm/i915: Eliminate weird parameter inversion from BXT PPS registers ...
author: Dave Airlie <airlied@redhat.com> 2015-10-30 02:45:33 +0300
committer: Dave Airlie <airlied@redhat.com> 2015-10-30 02:45:33 +0300
commit: 974e59ba0bc3bcc94d11fce9b34c10af32b5930f (patch)
tree: 51a970b2035018591ce0669aafc065ff20a80ee7
parent: d7e1bc3f5e70c5a106606e33cfa4d413459611ba (diff)
parent: 606bb5e0b28b540685fb94c22902cd9a948a3779 (diff)
download: linux-974e59ba0bc3bcc94d11fce9b34c10af32b5930f.tar.xz
25 files changed, 792 insertions, 639 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index 5f467845ef72..95c6bcb6bf22 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3584,6 +3584,7 @@ M:	Daniel Vetter <daniel.vetter@intel.com>
 M:	Jani Nikula <jani.nikula@linux.intel.com>
 L:	intel-gfx@lists.freedesktop.org
 L:	dri-devel@lists.freedesktop.org
+W:	https://01.org/linuxgraphics/
 Q:	http://patchwork.freedesktop.org/project/intel-gfx/
 T:	git git://anongit.freedesktop.org/drm-intel
 S:	Supported
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 3f2a7a7c7cd4..a3b22bdacd44 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1850,7 +1850,7 @@ static int i915_opregion(struct seq_file *m, void *unused)
 		goto out;
 
 	if (opregion->header) {
-		memcpy_fromio(data, opregion->header, OPREGION_SIZE);
+		memcpy(data, opregion->header, OPREGION_SIZE);
 		seq_write(m, data, OPREGION_SIZE);
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 5adba06a85d1..8afda459a26e 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -450,14 +450,14 @@ struct opregion_swsci;
 struct opregion_asle;
 
 struct intel_opregion {
-	struct opregion_header __iomem *header;
-	struct opregion_acpi __iomem *acpi;
-	struct opregion_swsci __iomem *swsci;
+	struct opregion_header *header;
+	struct opregion_acpi *acpi;
+	struct opregion_swsci *swsci;
 	u32 swsci_gbda_sub_functions;
 	u32 swsci_sbcb_sub_functions;
-	struct opregion_asle __iomem *asle;
-	void __iomem *vbt;
-	u32 __iomem *lid_state;
+	struct opregion_asle *asle;
+	void *vbt;
+	u32 *lid_state;
 	struct work_struct asle_work;
 };
 #define OPREGION_SIZE            (8*1024)
@@ -628,6 +628,10 @@ struct drm_i915_display_funcs {
 			  struct dpll *match_clock,
 			  struct dpll *best_clock);
 	void (*update_wm)(struct drm_crtc *crtc);
+	void (*update_sprite_wm)(struct drm_plane *plane,
+				 struct drm_crtc *crtc,
+				 uint32_t sprite_width, uint32_t sprite_height,
+				 int pixel_size, bool enable, bool scaled);
 	int (*modeset_calc_cdclk)(struct drm_atomic_state *state);
 	void (*modeset_commit_cdclk)(struct drm_atomic_state *state);
 	/* Returns the active state of the crtc, and if the crtc is active,
@@ -1031,7 +1035,7 @@ struct i915_suspend_saved_registers {
 	u32 saveMI_ARB_STATE;
 	u32 saveSWF0[16];
 	u32 saveSWF1[16];
-	u32 saveSWF2[3];
+	u32 saveSWF3[3];
 	uint64_t saveFENCE[I915_MAX_NUM_FENCES];
 	u32 savePCH_PORT_HOTPLUG;
 	u16 saveGCDGMBUS;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 1e67484fd5dc..e57061ac0219 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3657,53 +3657,106 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 	return 0;
 }
 
+/**
+ * Changes the cache-level of an object across all VMA.
+ *
+ * After this function returns, the object will be in the new cache-level
+ * across all GTT and the contents of the backing storage will be coherent,
+ * with respect to the new cache-level. In order to keep the backing storage
+ * coherent for all users, we only allow a single cache level to be set
+ * globally on the object and prevent it from being changed whilst the
+ * hardware is reading from the object. That is if the object is currently
+ * on the scanout it will be set to uncached (or equivalent display
+ * cache coherency) and all non-MOCS GPU access will also be uncached so
+ * that all direct access to the scanout remains coherent.
+ */
 int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 				    enum i915_cache_level cache_level)
 {
 	struct drm_device *dev = obj->base.dev;
 	struct i915_vma *vma, *next;
+	bool bound = false;
 	int ret = 0;
 
 	if (obj->cache_level == cache_level)
 		goto out;
 
-	if (i915_gem_obj_is_pinned(obj)) {
-		DRM_DEBUG("can not change the cache level of pinned objects\n");
-		return -EBUSY;
-	}
-
+	/* Inspect the list of currently bound VMA and unbind any that would
+	 * be invalid given the new cache-level. This is principally to
+	 * catch the issue of the CS prefetch crossing page boundaries and
+	 * reading an invalid PTE on older architectures.
+	 */
 	list_for_each_entry_safe(vma, next, &obj->vma_list, vma_link) {
+		if (!drm_mm_node_allocated(&vma->node))
+			continue;
+
+		if (vma->pin_count) {
+			DRM_DEBUG("can not change the cache level of pinned objects\n");
+			return -EBUSY;
+		}
+
 		if (!i915_gem_valid_gtt_space(vma, cache_level)) {
 			ret = i915_vma_unbind(vma);
 			if (ret)
 				return ret;
-		}
+		} else
+			bound = true;
 	}
 
-	if (i915_gem_obj_bound_any(obj)) {
+	/* We can reuse the existing drm_mm nodes but need to change the
+	 * cache-level on the PTE. We could simply unbind them all and
+	 * rebind with the correct cache-level on next use. However since
+	 * we already have a valid slot, dma mapping, pages etc, we may as
+	 * rewrite the PTE in the belief that doing so tramples upon less
+	 * state and so involves less work.
+	 */
+	if (bound) {
+		/* Before we change the PTE, the GPU must not be accessing it.
+		 * If we wait upon the object, we know that all the bound
+		 * VMA are no longer active.
+		 */
 		ret = i915_gem_object_wait_rendering(obj, false);
 		if (ret)
 			return ret;
 
-		i915_gem_object_finish_gtt(obj);
-
-		/* Before SandyBridge, you could not use tiling or fence
-		 * registers with snooped memory, so relinquish any fences
-		 * currently pointing to our region in the aperture.
-		 */
-		if (INTEL_INFO(dev)->gen < 6) {
+		if (!HAS_LLC(dev) && cache_level != I915_CACHE_NONE) {
+			/* Access to snoopable pages through the GTT is
+			 * incoherent and on some machines causes a hard
+			 * lockup. Relinquish the CPU mmaping to force
+			 * userspace to refault in the pages and we can
+			 * then double check if the GTT mapping is still
+			 * valid for that pointer access.
+			 */
+			i915_gem_release_mmap(obj);
+
+			/* As we no longer need a fence for GTT access,
+			 * we can relinquish it now (and so prevent having
+			 * to steal a fence from someone else on the next
+			 * fence request). Note GPU activity would have
+			 * dropped the fence as all snoopable access is
+			 * supposed to be linear.
+			 */
 			ret = i915_gem_object_put_fence(obj);
 			if (ret)
 				return ret;
+		} else {
+			/* We either have incoherent backing store and
+			 * so no GTT access or the architecture is fully
+			 * coherent. In such cases, existing GTT mmaps
+			 * ignore the cache bit in the PTE and we can
+			 * rewrite it without confusing the GPU or having
+			 * to force userspace to fault back in its mmaps.
+			 */
 		}
 
-		list_for_each_entry(vma, &obj->vma_list, vma_link)
-			if (drm_mm_node_allocated(&vma->node)) {
-				ret = i915_vma_bind(vma, cache_level,
-						    PIN_UPDATE);
-				if (ret)
-					return ret;
-			}
+		list_for_each_entry(vma, &obj->vma_list, vma_link) {
+			if (!drm_mm_node_allocated(&vma->node))
+				continue;
+
+			ret = i915_vma_bind(vma, cache_level, PIN_UPDATE);
+			if (ret)
+				return ret;
+		}
 	}
 
 	list_for_each_entry(vma, &obj->vma_list, vma_link)
@@ -3711,6 +3764,10 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 	obj->cache_level = cache_level;
 
 out:
+	/* Flush the dirty CPU caches to the backing storage so that the
+	 * object is now coherent at its new cache level (with respect
+	 * to the access domain).
+	 */
 	if (obj->cache_dirty &&
 	    obj->base.write_domain != I915_GEM_DOMAIN_CPU &&
 	    cpu_write_needs_clflush(obj)) {
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 620d57e2526b..43f35d12b677 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2502,6 +2502,36 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 			 enum i915_cache_level cache_level,
 			 u32 flags)
 {
+	struct drm_i915_gem_object *obj = vma->obj;
+	u32 pte_flags = 0;
+	int ret;
+
+	ret = i915_get_ggtt_vma_pages(vma);
+	if (ret)
+		return ret;
+
+	/* Currently applicable only to VLV */
+	if (obj->gt_ro)
+		pte_flags |= PTE_READ_ONLY;
+
+	vma->vm->insert_entries(vma->vm, vma->ggtt_view.pages,
+				vma->node.start,
+				cache_level, pte_flags);
+
+	/*
+	 * Without aliasing PPGTT there's no difference between
+	 * GLOBAL/LOCAL_BIND, it's all the same ptes. Hence unconditionally
+	 * upgrade to both bound if we bind either to avoid double-binding.
+	 */
+	vma->bound |= GLOBAL_BIND | LOCAL_BIND;
+
+	return 0;
+}
+
+static int aliasing_gtt_bind_vma(struct i915_vma *vma,
+				 enum i915_cache_level cache_level,
+				 u32 flags)
+{
 	struct drm_device *dev = vma->vm->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj = vma->obj;
@@ -2519,23 +2549,13 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 		pte_flags |= PTE_READ_ONLY;
 
 
-	if (!dev_priv->mm.aliasing_ppgtt || flags & GLOBAL_BIND) {
+	if (flags & GLOBAL_BIND) {
 		vma->vm->insert_entries(vma->vm, pages,
 					vma->node.start,
 					cache_level, pte_flags);
-
-		/* Note the inconsistency here is due to absence of the
-		 * aliasing ppgtt on gen4 and earlier. Though we always
-		 * request PIN_USER for execbuffer (translated to LOCAL_BIND),
-		 * without the appgtt, we cannot honour that request and so
-		 * must substitute it with a global binding. Since we do this
-		 * behind the upper layers back, we need to explicitly set
-		 * the bound flag ourselves.
-		 */
-		vma->bound |= GLOBAL_BIND;
 	}
 
-	if (dev_priv->mm.aliasing_ppgtt && flags & LOCAL_BIND) {
+	if (flags & LOCAL_BIND) {
 		struct i915_hw_ppgtt *appgtt = dev_priv->mm.aliasing_ppgtt;
 		appgtt->base.insert_entries(&appgtt->base, pages,
 					    vma->node.start,
@@ -2699,6 +2719,8 @@ static int i915_gem_setup_global_gtt(struct drm_device *dev,
 					true);
 
 		dev_priv->mm.aliasing_ppgtt = ppgtt;
+		WARN_ON(dev_priv->gtt.base.bind_vma != ggtt_bind_vma);
+		dev_priv->gtt.base.bind_vma = aliasing_gtt_bind_vma;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 4fb8a2f56281..d68328fa175b 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -139,27 +139,30 @@ static const u32 hpd_bxt[HPD_NUM_PINS] = {
 /*
  * We should clear IMR at preinstall/uninstall, and just check at postinstall.
  */
-#define GEN5_ASSERT_IIR_IS_ZERO(reg) do { \
-	u32 val = I915_READ(reg); \
-	if (val) { \
-		WARN(1, "Interrupt register 0x%x is not zero: 0x%08x\n", \
-		     (reg), val); \
-		I915_WRITE((reg), 0xffffffff); \
-		POSTING_READ(reg); \
-		I915_WRITE((reg), 0xffffffff); \
-		POSTING_READ(reg); \
-	} \
-} while (0)
+static void gen5_assert_iir_is_zero(struct drm_i915_private *dev_priv, u32 reg)
+{
+	u32 val = I915_READ(reg);
+
+	if (val == 0)
+		return;
+
+	WARN(1, "Interrupt register 0x%x is not zero: 0x%08x\n",
+	     reg, val);
+	I915_WRITE(reg, 0xffffffff);
+	POSTING_READ(reg);
+	I915_WRITE(reg, 0xffffffff);
+	POSTING_READ(reg);
+}
 
 #define GEN8_IRQ_INIT_NDX(type, which, imr_val, ier_val) do { \
-	GEN5_ASSERT_IIR_IS_ZERO(GEN8_##type##_IIR(which)); \
+	gen5_assert_iir_is_zero(dev_priv, GEN8_##type##_IIR(which)); \
 	I915_WRITE(GEN8_##type##_IER(which), (ier_val)); \
 	I915_WRITE(GEN8_##type##_IMR(which), (imr_val)); \
 	POSTING_READ(GEN8_##type##_IMR(which)); \
 } while (0)
 
 #define GEN5_IRQ_INIT(type, imr_val, ier_val) do { \
-	GEN5_ASSERT_IIR_IS_ZERO(type##IIR); \
+	gen5_assert_iir_is_zero(dev_priv, type##IIR); \
 	I915_WRITE(type##IER, (ier_val)); \
 	I915_WRITE(type##IMR, (imr_val)); \
 	POSTING_READ(type##IMR); \
@@ -707,12 +710,11 @@ static u32 i915_get_vblank_counter(struct drm_device *dev, unsigned int pipe)
 	return (((high1 << 8) | low) + (pixel >= vbl_start)) & 0xffffff;
 }
 
-static u32 gm45_get_vblank_counter(struct drm_device *dev, unsigned int pipe)
+static u32 g4x_get_vblank_counter(struct drm_device *dev, unsigned int pipe)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int reg = PIPE_FRMCOUNT_GM45(pipe);
 
-	return I915_READ(reg);
+	return I915_READ(PIPE_FRMCOUNT_G4X(pipe));
 }
 
 /* raw reads, only for fast reads of display block, no need for forcewake etc. */
@@ -3365,7 +3367,7 @@ static void ibx_irq_postinstall(struct drm_device *dev)
 	else
 		mask = SDE_GMBUS_CPT | SDE_AUX_MASK_CPT;
 
-	GEN5_ASSERT_IIR_IS_ZERO(SDEIIR);
+	gen5_assert_iir_is_zero(dev_priv, SDEIIR);
 	I915_WRITE(SDEIMR, ~mask);
 }
 
@@ -4397,7 +4399,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 		dev->driver->get_vblank_counter = i8xx_get_vblank_counter;
 	} else if (IS_G4X(dev_priv) || INTEL_INFO(dev_priv)->gen >= 5) {
 		dev->max_vblank_count = 0xffffffff; /* full 32 bit counter */
-		dev->driver->get_vblank_counter = gm45_get_vblank_counter;
+		dev->driver->get_vblank_counter = g4x_get_vblank_counter;
 	} else {
 		dev->driver->get_vblank_counter = i915_get_vblank_counter;
 		dev->max_vblank_count = 0xffffff; /* only 24 bits of frame count */
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 6be853d2233c..bc7b8faba84d 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -429,7 +429,7 @@
 #define   ASYNC_FLIP                (1<<22)
 #define   DISPLAY_PLANE_A           (0<<20)
 #define   DISPLAY_PLANE_B           (1<<20)
-#define GFX_OP_PIPE_CONTROL(len)	((0x3<<29)|(0x3<<27)|(0x2<<24)|(len-2))
+#define GFX_OP_PIPE_CONTROL(len)	((0x3<<29)|(0x3<<27)|(0x2<<24)|((len)-2))
 #define   PIPE_CONTROL_FLUSH_L3				(1<<27)
 #define   PIPE_CONTROL_GLOBAL_GTT_IVB			(1<<24) /* gen7+ */
 #define   PIPE_CONTROL_MMIO_WRITE			(1<<23)
@@ -1255,7 +1255,7 @@ enum skl_disp_power_wells {
 #define  PORT_PLL_DCO_AMP_OVR_EN_H	(1<<27)
 #define  PORT_PLL_DCO_AMP_DEFAULT	15
 #define  PORT_PLL_DCO_AMP_MASK		0x3c00
-#define  PORT_PLL_DCO_AMP(x)		(x<<10)
+#define  PORT_PLL_DCO_AMP(x)		((x)<<10)
 #define _PORT_PLL_BASE(port)		_PORT3(port, _PORT_PLL_0_A,	\
 						_PORT_PLL_0_B,		\
 						_PORT_PLL_0_C)
@@ -1552,8 +1552,8 @@ enum skl_disp_power_wells {
 #define RENDER_HWS_PGA_GEN7	(0x04080)
 #define RING_FAULT_REG(ring)	(0x4094 + 0x100*(ring)->id)
 #define   RING_FAULT_GTTSEL_MASK (1<<11)
-#define   RING_FAULT_SRCID(x)	((x >> 3) & 0xff)
-#define   RING_FAULT_FAULT_TYPE(x) ((x >> 1) & 0x3)
+#define   RING_FAULT_SRCID(x)	(((x) >> 3) & 0xff)
+#define   RING_FAULT_FAULT_TYPE(x) (((x) >> 1) & 0x3)
 #define   RING_FAULT_VALID	(1<<0)
 #define DONE_REG		0x40b0
 #define GEN8_PRIVATE_PAT_LO	0x40e0
@@ -1641,9 +1641,9 @@ enum skl_disp_power_wells {
 #define   ERR_INT_PIPE_CRC_DONE_B	(1<<5)
 #define   ERR_INT_FIFO_UNDERRUN_B	(1<<3)
 #define   ERR_INT_PIPE_CRC_DONE_A	(1<<2)
-#define   ERR_INT_PIPE_CRC_DONE(pipe)	(1<<(2 + pipe*3))
+#define   ERR_INT_PIPE_CRC_DONE(pipe)	(1<<(2 + (pipe)*3))
 #define   ERR_INT_FIFO_UNDERRUN_A	(1<<0)
-#define   ERR_INT_FIFO_UNDERRUN(pipe)	(1<<(pipe*3))
+#define   ERR_INT_FIFO_UNDERRUN(pipe)	(1<<((pipe)*3))
 
 #define GEN8_FAULT_TLB_DATA0		0x04b10
 #define GEN8_FAULT_TLB_DATA1		0x04b14
@@ -1704,8 +1704,8 @@ enum skl_disp_power_wells {
 #define   GEN6_WIZ_HASHING_16x4				GEN6_WIZ_HASHING(1, 0)
 #define   GEN6_WIZ_HASHING_MASK				GEN6_WIZ_HASHING(1, 1)
 #define   GEN6_TD_FOUR_ROW_DISPATCH_DISABLE		(1 << 5)
-#define   GEN9_IZ_HASHING_MASK(slice)			(0x3 << (slice * 2))
-#define   GEN9_IZ_HASHING(slice, val)			((val) << (slice * 2))
+#define   GEN9_IZ_HASHING_MASK(slice)			(0x3 << ((slice) * 2))
+#define   GEN9_IZ_HASHING(slice, val)			((val) << ((slice) * 2))
 
 #define GFX_MODE	0x02520
 #define GFX_MODE_GEN7	0x0229c
@@ -2144,7 +2144,7 @@ enum skl_disp_power_wells {
 # define GPIO_DATA_VAL_IN		(1 << 12)
 # define GPIO_DATA_PULLUP_DISABLE	(1 << 13)
 
-#define GMBUS0			0x5100 /* clock/port select */
+#define GMBUS0			(dev_priv->gpio_mmio_base + 0x5100) /* clock/port select */
 #define   GMBUS_RATE_100KHZ	(0<<8)
 #define   GMBUS_RATE_50KHZ	(1<<8)
 #define   GMBUS_RATE_400KHZ	(2<<8) /* reserved on Pineview */
@@ -2163,7 +2163,7 @@ enum skl_disp_power_wells {
 #define   GMBUS_PIN_2_BXT	2
 #define   GMBUS_PIN_3_BXT	3
 #define   GMBUS_NUM_PINS	7 /* including 0 */
-#define GMBUS1			0x5104 /* command/status */
+#define GMBUS1			(dev_priv->gpio_mmio_base + 0x5104) /* command/status */
 #define   GMBUS_SW_CLR_INT	(1<<31)
 #define   GMBUS_SW_RDY		(1<<30)
 #define   GMBUS_ENT		(1<<29) /* enable timeout */
@@ -2177,7 +2177,7 @@ enum skl_disp_power_wells {
 #define   GMBUS_SLAVE_ADDR_SHIFT 1
 #define   GMBUS_SLAVE_READ	(1<<0)
 #define   GMBUS_SLAVE_WRITE	(0<<0)
-#define GMBUS2			0x5108 /* status */
+#define GMBUS2			(dev_priv->gpio_mmio_base + 0x5108) /* status */
 #define   GMBUS_INUSE		(1<<15)
 #define   GMBUS_HW_WAIT_PHASE	(1<<14)
 #define   GMBUS_STALL_TIMEOUT	(1<<13)
@@ -2185,14 +2185,14 @@ enum skl_disp_power_wells {
 #define   GMBUS_HW_RDY		(1<<11)
 #define   GMBUS_SATOER		(1<<10)
 #define   GMBUS_ACTIVE		(1<<9)
-#define GMBUS3			0x510c /* data buffer bytes 3-0 */
-#define GMBUS4			0x5110 /* interrupt mask (Pineview+) */
+#define GMBUS3			(dev_priv->gpio_mmio_base + 0x510c) /* data buffer bytes 3-0 */
+#define GMBUS4			(dev_priv->gpio_mmio_base + 0x5110) /* interrupt mask (Pineview+) */
 #define   GMBUS_SLAVE_TIMEOUT_EN (1<<4)
 #define   GMBUS_NAK_EN		(1<<3)
 #define   GMBUS_IDLE_EN		(1<<2)
 #define   GMBUS_HW_WAIT_EN	(1<<1)
 #define   GMBUS_HW_RDY_EN	(1<<0)
-#define GMBUS5			0x5120 /* byte index */
+#define GMBUS5			(dev_priv->gpio_mmio_base + 0x5120) /* byte index */
 #define   GMBUS_2BYTE_INDEX_EN	(1<<31)
 
 /*
@@ -2866,21 +2866,21 @@ enum skl_disp_power_wells {
  *   doesn't need saving on GT1
  */
 #define CXT_SIZE		0x21a0
-#define GEN6_CXT_POWER_SIZE(cxt_reg)	((cxt_reg >> 24) & 0x3f)
-#define GEN6_CXT_RING_SIZE(cxt_reg)	((cxt_reg >> 18) & 0x3f)
-#define GEN6_CXT_RENDER_SIZE(cxt_reg)	((cxt_reg >> 12) & 0x3f)
-#define GEN6_CXT_EXTENDED_SIZE(cxt_reg)	((cxt_reg >> 6) & 0x3f)
-#define GEN6_CXT_PIPELINE_SIZE(cxt_reg)	((cxt_reg >> 0) & 0x3f)
+#define GEN6_CXT_POWER_SIZE(cxt_reg)	(((cxt_reg) >> 24) & 0x3f)
+#define GEN6_CXT_RING_SIZE(cxt_reg)	(((cxt_reg) >> 18) & 0x3f)
+#define GEN6_CXT_RENDER_SIZE(cxt_reg)	(((cxt_reg) >> 12) & 0x3f)
+#define GEN6_CXT_EXTENDED_SIZE(cxt_reg)	(((cxt_reg) >> 6) & 0x3f)
+#define GEN6_CXT_PIPELINE_SIZE(cxt_reg)	(((cxt_reg) >> 0) & 0x3f)
 #define GEN6_CXT_TOTAL_SIZE(cxt_reg)	(GEN6_CXT_RING_SIZE(cxt_reg) + \
 					GEN6_CXT_EXTENDED_SIZE(cxt_reg) + \
 					GEN6_CXT_PIPELINE_SIZE(cxt_reg))
 #define GEN7_CXT_SIZE		0x21a8
-#define GEN7_CXT_POWER_SIZE(ctx_reg)	((ctx_reg >> 25) & 0x7f)
-#define GEN7_CXT_RING_SIZE(ctx_reg)	((ctx_reg >> 22) & 0x7)
-#define GEN7_CXT_RENDER_SIZE(ctx_reg)	((ctx_reg >> 16) & 0x3f)
-#define GEN7_CXT_EXTENDED_SIZE(ctx_reg)	((ctx_reg >> 9) & 0x7f)
-#define GEN7_CXT_GT1_SIZE(ctx_reg)	((ctx_reg >> 6) & 0x7)
-#define GEN7_CXT_VFSTATE_SIZE(ctx_reg)	((ctx_reg >> 0) & 0x3f)
+#define GEN7_CXT_POWER_SIZE(ctx_reg)	(((ctx_reg) >> 25) & 0x7f)
+#define GEN7_CXT_RING_SIZE(ctx_reg)	(((ctx_reg) >> 22) & 0x7)
+#define GEN7_CXT_RENDER_SIZE(ctx_reg)	(((ctx_reg) >> 16) & 0x3f)
+#define GEN7_CXT_EXTENDED_SIZE(ctx_reg)	(((ctx_reg) >> 9) & 0x7f)
+#define GEN7_CXT_GT1_SIZE(ctx_reg)	(((ctx_reg) >> 6) & 0x7)
+#define GEN7_CXT_VFSTATE_SIZE(ctx_reg)	(((ctx_reg) >> 0) & 0x3f)
 #define GEN7_CXT_TOTAL_SIZE(ctx_reg)	(GEN7_CXT_EXTENDED_SIZE(ctx_reg) + \
 					 GEN7_CXT_VFSTATE_SIZE(ctx_reg))
 /* Haswell does have the CXT_SIZE register however it does not appear to be
@@ -4284,7 +4284,7 @@ enum skl_disp_power_wells {
 #define   DP_AUX_CH_CTL_PSR_DATA_AUX_REG_SKL	(1 << 14)
 #define   DP_AUX_CH_CTL_FS_DATA_AUX_REG_SKL	(1 << 13)
 #define   DP_AUX_CH_CTL_GTC_DATA_AUX_REG_SKL	(1 << 12)
-#define   DP_AUX_CH_CTL_FW_SYNC_PULSE_SKL_MASK (1f << 5)
+#define   DP_AUX_CH_CTL_FW_SYNC_PULSE_SKL_MASK (0x1f << 5)
 #define   DP_AUX_CH_CTL_FW_SYNC_PULSE_SKL(c) (((c) - 1) << 5)
 #define   DP_AUX_CH_CTL_SYNC_PULSE_SKL(c)   ((c) - 1)
 
@@ -4846,10 +4846,10 @@ enum skl_disp_power_wells {
 #define   PIPE_PIXEL_MASK         0x00ffffff
 #define   PIPE_PIXEL_SHIFT        0
 /* GM45+ just has to be different */
-#define _PIPEA_FRMCOUNT_GM45	0x70040
-#define _PIPEA_FLIPCOUNT_GM45	0x70044
-#define PIPE_FRMCOUNT_GM45(pipe) _PIPE2(pipe, _PIPEA_FRMCOUNT_GM45)
-#define PIPE_FLIPCOUNT_GM45(pipe) _PIPE2(pipe, _PIPEA_FLIPCOUNT_GM45)
+#define _PIPEA_FRMCOUNT_G4X	0x70040
+#define _PIPEA_FLIPCOUNT_G4X	0x70044
+#define PIPE_FRMCOUNT_G4X(pipe) _PIPE2(pipe, _PIPEA_FRMCOUNT_G4X)
+#define PIPE_FLIPCOUNT_G4X(pipe) _PIPE2(pipe, _PIPEA_FLIPCOUNT_G4X)
 
 /* Cursor A & B regs */
 #define _CURACNTR		0x70080
@@ -4991,20 +4991,20 @@ enum skl_disp_power_wells {
 #define I915_LO_DISPBASE(val)	(val & ~DISP_BASEADDR_MASK)
 #define I915_HI_DISPBASE(val)	(val & DISP_BASEADDR_MASK)
 
-/* VBIOS flags */
-#define SWF00			(dev_priv->info.display_mmio_offset + 0x71410)
-#define SWF01			(dev_priv->info.display_mmio_offset + 0x71414)
-#define SWF02			(dev_priv->info.display_mmio_offset + 0x71418)
-#define SWF03			(dev_priv->info.display_mmio_offset + 0x7141c)
-#define SWF04			(dev_priv->info.display_mmio_offset + 0x71420)
-#define SWF05			(dev_priv->info.display_mmio_offset + 0x71424)
-#define SWF06			(dev_priv->info.display_mmio_offset + 0x71428)
-#define SWF10			(dev_priv->info.display_mmio_offset + 0x70410)
-#define SWF11			(dev_priv->info.display_mmio_offset + 0x70414)
-#define SWF14			(dev_priv->info.display_mmio_offset + 0x71420)
-#define SWF30			(dev_priv->info.display_mmio_offset + 0x72414)
-#define SWF31			(dev_priv->info.display_mmio_offset + 0x72418)
-#define SWF32			(dev_priv->info.display_mmio_offset + 0x7241c)
+/*
+ * VBIOS flags
+ * gen2:
+ * [00:06] alm,mgm
+ * [10:16] all
+ * [30:32] alm,mgm
+ * gen3+:
+ * [00:0f] all
+ * [10:1f] all
+ * [30:32] all
+ */
+#define SWF0(i)	(dev_priv->info.display_mmio_offset + 0x70410 + (i) * 4)
+#define SWF1(i)	(dev_priv->info.display_mmio_offset + 0x71410 + (i) * 4)
+#define SWF3(i)	(dev_priv->info.display_mmio_offset + 0x72414 + (i) * 4)
 
 /* Pipe B */
 #define _PIPEBDSL		(dev_priv->info.display_mmio_offset + 0x71000)
@@ -5012,8 +5012,8 @@ enum skl_disp_power_wells {
 #define _PIPEBSTAT		(dev_priv->info.display_mmio_offset + 0x71024)
 #define _PIPEBFRAMEHIGH		0x71040
 #define _PIPEBFRAMEPIXEL	0x71044
-#define _PIPEB_FRMCOUNT_GM45	(dev_priv->info.display_mmio_offset + 0x71040)
-#define _PIPEB_FLIPCOUNT_GM45	(dev_priv->info.display_mmio_offset + 0x71044)
+#define _PIPEB_FRMCOUNT_G4X	(dev_priv->info.display_mmio_offset + 0x71040)
+#define _PIPEB_FLIPCOUNT_G4X	(dev_priv->info.display_mmio_offset + 0x71044)
 
 
 /* Display B control */
@@ -5223,18 +5223,18 @@ enum skl_disp_power_wells {
 #define _SPBCONSTALPHA		(VLV_DISPLAY_BASE + 0x722a8)
 #define _SPBGAMC		(VLV_DISPLAY_BASE + 0x722f4)
 
-#define SPCNTR(pipe, plane) _PIPE(pipe * 2 + plane, _SPACNTR, _SPBCNTR)
-#define SPLINOFF(pipe, plane) _PIPE(pipe * 2 + plane, _SPALINOFF, _SPBLINOFF)
-#define SPSTRIDE(pipe, plane) _PIPE(pipe * 2 + plane, _SPASTRIDE, _SPBSTRIDE)
-#define SPPOS(pipe, plane) _PIPE(pipe * 2 + plane, _SPAPOS, _SPBPOS)
-#define SPSIZE(pipe, plane) _PIPE(pipe * 2 + plane, _SPASIZE, _SPBSIZE)
-#define SPKEYMINVAL(pipe, plane) _PIPE(pipe * 2 + plane, _SPAKEYMINVAL, _SPBKEYMINVAL)
-#define SPKEYMSK(pipe, plane) _PIPE(pipe * 2 + plane, _SPAKEYMSK, _SPBKEYMSK)
-#define SPSURF(pipe, plane) _PIPE(pipe * 2 + plane, _SPASURF, _SPBSURF)
-#define SPKEYMAXVAL(pipe, plane) _PIPE(pipe * 2 + plane, _SPAKEYMAXVAL, _SPBKEYMAXVAL)
-#define SPTILEOFF(pipe, plane) _PIPE(pipe * 2 + plane, _SPATILEOFF, _SPBTILEOFF)
-#define SPCONSTALPHA(pipe, plane) _PIPE(pipe * 2 + plane, _SPACONSTALPHA, _SPBCONSTALPHA)
-#define SPGAMC(pipe, plane) _PIPE(pipe * 2 + plane, _SPAGAMC, _SPBGAMC)
+#define SPCNTR(pipe, plane) _PIPE((pipe) * 2 + (plane), _SPACNTR, _SPBCNTR)
+#define SPLINOFF(pipe, plane) _PIPE((pipe) * 2 + (plane), _SPALINOFF, _SPBLINOFF)
+#define SPSTRIDE(pipe, plane) _PIPE((pipe) * 2 + (plane), _SPASTRIDE, _SPBSTRIDE)
+#define SPPOS(pipe, plane) _PIPE((pipe) * 2 + (plane), _SPAPOS, _SPBPOS)
+#define SPSIZE(pipe, plane) _PIPE((pipe) * 2 + (plane), _SPASIZE, _SPBSIZE)
+#define SPKEYMINVAL(pipe, plane) _PIPE((pipe) * 2 + (plane), _SPAKEYMINVAL, _SPBKEYMINVAL)
+#define SPKEYMSK(pipe, plane) _PIPE((pipe) * 2 + (plane), _SPAKEYMSK, _SPBKEYMSK)
+#define SPSURF(pipe, plane) _PIPE((pipe) * 2 + (plane), _SPASURF, _SPBSURF)
+#define SPKEYMAXVAL(pipe, plane) _PIPE((pipe) * 2 + (plane), _SPAKEYMAXVAL, _SPBKEYMAXVAL)
+#define SPTILEOFF(pipe, plane) _PIPE((pipe) * 2 + (plane), _SPATILEOFF, _SPBTILEOFF)
+#define SPCONSTALPHA(pipe, plane) _PIPE((pipe) * 2 + (plane), _SPACONSTALPHA, _SPBCONSTALPHA)
+#define SPGAMC(pipe, plane) _PIPE((pipe) * 2 + (plane), _SPAGAMC, _SPBGAMC)
 
 /*
  * CHV pipe B sprite CSC
@@ -5580,7 +5580,7 @@ enum skl_disp_power_wells {
 #define PS_SCALER_MODE_DYN  (0 << 28)
 #define PS_SCALER_MODE_HQ  (1 << 28)
 #define PS_PLANE_SEL_MASK  (7 << 25)
-#define PS_PLANE_SEL(plane) ((plane + 1) << 25)
+#define PS_PLANE_SEL(plane) (((plane) + 1) << 25)
 #define PS_FILTER_MASK         (3 << 23)
 #define PS_FILTER_MEDIUM       (0 << 23)
 #define PS_FILTER_EDGE_ENHANCE (2 << 23)
@@ -5745,7 +5745,7 @@ enum skl_disp_power_wells {
 #define DE_PLANEA_FLIP_DONE_IVB		(1<<3)
 #define DE_PLANE_FLIP_DONE_IVB(plane)	(1<< (3 + 5*(plane)))
 #define DE_PIPEA_VBLANK_IVB		(1<<0)
-#define DE_PIPE_VBLANK_IVB(pipe)	(1 << (pipe * 5))
+#define DE_PIPE_VBLANK_IVB(pipe)	(1 << ((pipe) * 5))
 
 #define VLV_MASTER_IER			0x4400c /* Gunit master IER */
 #define   MASTER_INTERRUPT_ENABLE	(1<<31)
@@ -5769,7 +5769,7 @@ enum skl_disp_power_wells {
 #define  GEN8_DE_PIPE_C_IRQ		(1<<18)
 #define  GEN8_DE_PIPE_B_IRQ		(1<<17)
 #define  GEN8_DE_PIPE_A_IRQ		(1<<16)
-#define  GEN8_DE_PIPE_IRQ(pipe)		(1<<(16+pipe))
+#define  GEN8_DE_PIPE_IRQ(pipe)		(1<<(16+(pipe)))
 #define  GEN8_GT_VECS_IRQ		(1<<6)
 #define  GEN8_GT_PM_IRQ			(1<<4)
 #define  GEN8_GT_VCS2_IRQ		(1<<3)
@@ -5813,7 +5813,7 @@ enum skl_disp_power_wells {
 #define  GEN9_PIPE_PLANE3_FLIP_DONE	(1 << 5)
 #define  GEN9_PIPE_PLANE2_FLIP_DONE	(1 << 4)
 #define  GEN9_PIPE_PLANE1_FLIP_DONE	(1 << 3)
-#define  GEN9_PIPE_PLANE_FLIP_DONE(p)	(1 << (3 + p))
+#define  GEN9_PIPE_PLANE_FLIP_DONE(p)	(1 << (3 + (p)))
 #define GEN8_DE_PIPE_IRQ_FAULT_ERRORS \
 	(GEN8_PIPE_CURSOR_FAULT | \
 	 GEN8_PIPE_SPRITE_FAULT | \
@@ -6072,7 +6072,7 @@ enum skl_disp_power_wells {
 #define  SERR_INT_TRANS_C_FIFO_UNDERRUN	(1<<6)
 #define  SERR_INT_TRANS_B_FIFO_UNDERRUN	(1<<3)
 #define  SERR_INT_TRANS_A_FIFO_UNDERRUN	(1<<0)
-#define  SERR_INT_TRANS_FIFO_UNDERRUN(pipe)	(1<<(pipe*3))
+#define  SERR_INT_TRANS_FIFO_UNDERRUN(pipe)	(1<<((pipe)*3))
 
 /* digital port hotplug */
 #define PCH_PORT_HOTPLUG		0xc4030	/* SHOTPLUG_CTL */
@@ -6183,9 +6183,9 @@ enum skl_disp_power_wells {
 #define PCH_SSC4_AUX_PARMS      0xc6214
 
 #define PCH_DPLL_SEL		0xc7000
-#define	 TRANS_DPLLB_SEL(pipe)		(1 << (pipe * 4))
+#define	 TRANS_DPLLB_SEL(pipe)		(1 << ((pipe) * 4))
 #define	 TRANS_DPLLA_SEL(pipe)		0
-#define  TRANS_DPLL_ENABLE(pipe)	(1 << (pipe * 4 + 3))
+#define  TRANS_DPLL_ENABLE(pipe)	(1 << ((pipe) * 4 + 3))
 
 /* transcoder */
 
@@ -6286,16 +6286,16 @@ enum skl_disp_power_wells {
 
 #define HSW_TVIDEO_DIP_CTL(trans) \
 	 _TRANSCODER2(trans, HSW_VIDEO_DIP_CTL_A)
-#define HSW_TVIDEO_DIP_AVI_DATA(trans) \
-	 _TRANSCODER2(trans, HSW_VIDEO_DIP_AVI_DATA_A)
-#define HSW_TVIDEO_DIP_VS_DATA(trans) \
-	 _TRANSCODER2(trans, HSW_VIDEO_DIP_VS_DATA_A)
-#define HSW_TVIDEO_DIP_SPD_DATA(trans) \
-	 _TRANSCODER2(trans, HSW_VIDEO_DIP_SPD_DATA_A)
+#define HSW_TVIDEO_DIP_AVI_DATA(trans, i) \
+	(_TRANSCODER2(trans, HSW_VIDEO_DIP_AVI_DATA_A) + (i) * 4)
+#define HSW_TVIDEO_DIP_VS_DATA(trans, i) \
+	(_TRANSCODER2(trans, HSW_VIDEO_DIP_VS_DATA_A) + (i) * 4)
+#define HSW_TVIDEO_DIP_SPD_DATA(trans, i) \
+	(_TRANSCODER2(trans, HSW_VIDEO_DIP_SPD_DATA_A) + (i) * 4)
 #define HSW_TVIDEO_DIP_GCP(trans) \
 	_TRANSCODER2(trans, HSW_VIDEO_DIP_GCP_A)
-#define HSW_TVIDEO_DIP_VSC_DATA(trans) \
-	 _TRANSCODER2(trans, HSW_VIDEO_DIP_VSC_DATA_A)
+#define HSW_TVIDEO_DIP_VSC_DATA(trans, i) \
+	(_TRANSCODER2(trans, HSW_VIDEO_DIP_VSC_DATA_A) + (i) * 4)
 
 #define HSW_STEREO_3D_CTL_A	0x70020
 #define   S3D_ENABLE		(1<<31)
@@ -6587,10 +6587,10 @@ enum skl_disp_power_wells {
 #define _BXT_PP_ON_DELAYS2	0xc7308
 #define _BXT_PP_OFF_DELAYS2	0xc730c
 
-#define BXT_PP_STATUS(n)	((!n) ? PCH_PP_STATUS : _BXT_PP_STATUS2)
-#define BXT_PP_CONTROL(n)	((!n) ? PCH_PP_CONTROL : _BXT_PP_CONTROL2)
-#define BXT_PP_ON_DELAYS(n)	((!n) ? PCH_PP_ON_DELAYS : _BXT_PP_ON_DELAYS2)
-#define BXT_PP_OFF_DELAYS(n)	((!n) ? PCH_PP_OFF_DELAYS : _BXT_PP_OFF_DELAYS2)
+#define BXT_PP_STATUS(n)	_PIPE(n, PCH_PP_STATUS, _BXT_PP_STATUS2)
+#define BXT_PP_CONTROL(n)	_PIPE(n, PCH_PP_CONTROL, _BXT_PP_CONTROL2)
+#define BXT_PP_ON_DELAYS(n)	_PIPE(n, PCH_PP_ON_DELAYS, _BXT_PP_ON_DELAYS2)
+#define BXT_PP_OFF_DELAYS(n)	_PIPE(n, PCH_PP_OFF_DELAYS, _BXT_PP_OFF_DELAYS2)
 
 #define PCH_DP_B		0xe4100
 #define PCH_DPB_AUX_CH_CTL	0xe4110
@@ -7348,7 +7348,7 @@ enum skl_disp_power_wells {
 #define TRANS_CLK_SEL(tran) _TRANSCODER(tran, TRANS_CLK_SEL_A, TRANS_CLK_SEL_B)
 /* For each transcoder, we need to select the corresponding port clock */
 #define  TRANS_CLK_SEL_DISABLED		(0x0<<29)
-#define  TRANS_CLK_SEL_PORT(x)		((x+1)<<29)
+#define  TRANS_CLK_SEL_PORT(x)		(((x)+1)<<29)
 
 #define TRANSA_MSA_MISC			0x60410
 #define TRANSB_MSA_MISC			0x61410
@@ -7421,10 +7421,10 @@ enum skl_disp_power_wells {
 
 /* DPLL control2 */
 #define DPLL_CTRL2				0x6C05C
-#define  DPLL_CTRL2_DDI_CLK_OFF(port)		(1<<(port+15))
+#define  DPLL_CTRL2_DDI_CLK_OFF(port)		(1<<((port)+15))
 #define  DPLL_CTRL2_DDI_CLK_SEL_MASK(port)	(3<<((port)*3+1))
 #define  DPLL_CTRL2_DDI_CLK_SEL_SHIFT(port)    ((port)*3+1)
-#define  DPLL_CTRL2_DDI_CLK_SEL(clk, port)	(clk<<((port)*3+1))
+#define  DPLL_CTRL2_DDI_CLK_SEL(clk, port)	((clk)<<((port)*3+1))
 #define  DPLL_CTRL2_DDI_SEL_OVERRIDE(port)     (1<<((port)*3))
 
 /* DPLL Status */
@@ -7437,23 +7437,23 @@ enum skl_disp_power_wells {
 #define DPLL3_CFGCR1	0x6C050
 #define  DPLL_CFGCR1_FREQ_ENABLE	(1<<31)
 #define  DPLL_CFGCR1_DCO_FRACTION_MASK	(0x7fff<<9)
-#define  DPLL_CFGCR1_DCO_FRACTION(x)	(x<<9)
+#define  DPLL_CFGCR1_DCO_FRACTION(x)	((x)<<9)
 #define  DPLL_CFGCR1_DCO_INTEGER_MASK	(0x1ff)
 
 #define DPLL1_CFGCR2	0x6C044
 #define DPLL2_CFGCR2	0x6C04C
 #define DPLL3_CFGCR2	0x6C054
 #define  DPLL_CFGCR2_QDIV_RATIO_MASK	(0xff<<8)
-#define  DPLL_CFGCR2_QDIV_RATIO(x)	(x<<8)
-#define  DPLL_CFGCR2_QDIV_MODE(x)	(x<<7)
+#define  DPLL_CFGCR2_QDIV_RATIO(x)	((x)<<8)
+#define  DPLL_CFGCR2_QDIV_MODE(x)	((x)<<7)
 #define  DPLL_CFGCR2_KDIV_MASK		(3<<5)
-#define  DPLL_CFGCR2_KDIV(x)		(x<<5)
+#define  DPLL_CFGCR2_KDIV(x)		((x)<<5)
 #define  DPLL_CFGCR2_KDIV_5 (0<<5)
 #define  DPLL_CFGCR2_KDIV_2 (1<<5)
 #define  DPLL_CFGCR2_KDIV_3 (2<<5)
 #define  DPLL_CFGCR2_KDIV_1 (3<<5)
 #define  DPLL_CFGCR2_PDIV_MASK		(7<<2)
-#define  DPLL_CFGCR2_PDIV(x)		(x<<2)
+#define  DPLL_CFGCR2_PDIV(x)		((x)<<2)
 #define  DPLL_CFGCR2_PDIV_1 (0<<2)
 #define  DPLL_CFGCR2_PDIV_2 (1<<2)
 #define  DPLL_CFGCR2_PDIV_3 (2<<2)
@@ -7979,7 +7979,7 @@ enum skl_disp_power_wells {
 #define  VIRTUAL_CHANNEL_SHIFT				6
 #define  VIRTUAL_CHANNEL_MASK				(3 << 6)
 #define  DATA_TYPE_SHIFT				0
-#define  DATA_TYPE_MASK					(3f << 0)
+#define  DATA_TYPE_MASK					(0x3f << 0)
 /* data type values, see include/video/mipi_display.h */
 
 #define _MIPIA_GEN_FIFO_STAT		(dev_priv->mipi_mmio_base + 0xb074)
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index 1ccac618468e..2d9182189422 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -122,12 +122,24 @@ int i915_save_state(struct drm_device *dev)
 	dev_priv->regfile.saveMI_ARB_STATE = I915_READ(MI_ARB_STATE);
 
 	/* Scratch space */
-	for (i = 0; i < 16; i++) {
-		dev_priv->regfile.saveSWF0[i] = I915_READ(SWF00 + (i << 2));
-		dev_priv->regfile.saveSWF1[i] = I915_READ(SWF10 + (i << 2));
+	if (IS_GEN2(dev_priv) && IS_MOBILE(dev_priv)) {
+		for (i = 0; i < 7; i++) {
+			dev_priv->regfile.saveSWF0[i] = I915_READ(SWF0(i));
+			dev_priv->regfile.saveSWF1[i] = I915_READ(SWF1(i));
+		}
+		for (i = 0; i < 3; i++)
+			dev_priv->regfile.saveSWF3[i] = I915_READ(SWF3(i));
+	} else if (IS_GEN2(dev_priv)) {
+		for (i = 0; i < 7; i++)
+			dev_priv->regfile.saveSWF1[i] = I915_READ(SWF1(i));
+	} else if (HAS_GMCH_DISPLAY(dev_priv)) {
+		for (i = 0; i < 16; i++) {
+			dev_priv->regfile.saveSWF0[i] = I915_READ(SWF0(i));
+			dev_priv->regfile.saveSWF1[i] = I915_READ(SWF1(i));
+		}
+		for (i = 0; i < 3; i++)
+			dev_priv->regfile.saveSWF3[i] = I915_READ(SWF3(i));
 	}
-	for (i = 0; i < 3; i++)
-		dev_priv->regfile.saveSWF2[i] = I915_READ(SWF30 + (i << 2));
 
 	mutex_unlock(&dev->struct_mutex);
 
@@ -156,12 +168,25 @@ int i915_restore_state(struct drm_device *dev)
 	/* Memory arbitration state */
 	I915_WRITE(MI_ARB_STATE, dev_priv->regfile.saveMI_ARB_STATE | 0xffff0000);
 
-	for (i = 0; i < 16; i++) {
-		I915_WRITE(SWF00 + (i << 2), dev_priv->regfile.saveSWF0[i]);
-		I915_WRITE(SWF10 + (i << 2), dev_priv->regfile.saveSWF1[i]);
+	/* Scratch space */
+	if (IS_GEN2(dev_priv) && IS_MOBILE(dev_priv)) {
+		for (i = 0; i < 7; i++) {
+			I915_WRITE(SWF0(i), dev_priv->regfile.saveSWF0[i]);
+			I915_WRITE(SWF1(i), dev_priv->regfile.saveSWF1[i]);
+		}
+		for (i = 0; i < 3; i++)
+			I915_WRITE(SWF3(i), dev_priv->regfile.saveSWF3[i]);
+	} else if (IS_GEN2(dev_priv)) {
+		for (i = 0; i < 7; i++)
+			I915_WRITE(SWF1(i), dev_priv->regfile.saveSWF1[i]);
+	} else if (HAS_GMCH_DISPLAY(dev_priv)) {
+		for (i = 0; i < 16; i++) {
+			I915_WRITE(SWF0(i), dev_priv->regfile.saveSWF0[i]);
+			I915_WRITE(SWF1(i), dev_priv->regfile.saveSWF1[i]);
+		}
+		for (i = 0; i < 3; i++)
+			I915_WRITE(SWF3(i), dev_priv->regfile.saveSWF3[i]);
 	}
-	for (i = 0; i < 3; i++)
-		I915_WRITE(SWF30 + (i << 2), dev_priv->regfile.saveSWF2[i]);
 
 	mutex_unlock(&dev->struct_mutex);
 
diff --git a/drivers/gpu/drm/i915/intel_acpi.c b/drivers/gpu/drm/i915/intel_acpi.c
index 8b13b9d0373a..eb638a1e69d2 100644
--- a/drivers/gpu/drm/i915/intel_acpi.c
+++ b/drivers/gpu/drm/i915/intel_acpi.c
@@ -5,7 +5,6 @@
  */
 #include <linux/pci.h>
 #include <linux/acpi.h>
-#include <linux/vga_switcheroo.h>
 #include <drm/drmP.h>
 #include "i915_drv.h"
 
diff --git a/drivers/gpu/drm/i915/intel_atomic.c b/drivers/gpu/drm/i915/intel_atomic.c
index 05b12032d262..f1975f267710 100644
--- a/drivers/gpu/drm/i915/intel_atomic.c
+++ b/drivers/gpu/drm/i915/intel_atomic.c
@@ -94,7 +94,6 @@ intel_crtc_duplicate_state(struct drm_crtc *crtc)
 	__drm_atomic_helper_crtc_duplicate_state(crtc, &crtc_state->base);
 
 	crtc_state->update_pipe = false;
-	crtc_state->disable_lp_wm = false;
 
 	return &crtc_state->base;
 }
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 56c2f54801c4..4dccd9b003a1 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -61,21 +61,21 @@ static const struct {
 	int clock;
 	u32 config;
 } hdmi_audio_clock[] = {
-	{ DIV_ROUND_UP(25200 * 1000, 1001), AUD_CONFIG_PIXEL_CLOCK_HDMI_25175 },
+	{ 25175, AUD_CONFIG_PIXEL_CLOCK_HDMI_25175 },
 	{ 25200, AUD_CONFIG_PIXEL_CLOCK_HDMI_25200 }, /* default per bspec */
 	{ 27000, AUD_CONFIG_PIXEL_CLOCK_HDMI_27000 },
-	{ 27000 * 1001 / 1000, AUD_CONFIG_PIXEL_CLOCK_HDMI_27027 },
+	{ 27027, AUD_CONFIG_PIXEL_CLOCK_HDMI_27027 },
 	{ 54000, AUD_CONFIG_PIXEL_CLOCK_HDMI_54000 },
-	{ 54000 * 1001 / 1000, AUD_CONFIG_PIXEL_CLOCK_HDMI_54054 },
-	{ DIV_ROUND_UP(74250 * 1000, 1001), AUD_CONFIG_PIXEL_CLOCK_HDMI_74176 },
+	{ 54054, AUD_CONFIG_PIXEL_CLOCK_HDMI_54054 },
+	{ 74176, AUD_CONFIG_PIXEL_CLOCK_HDMI_74176 },
 	{ 74250, AUD_CONFIG_PIXEL_CLOCK_HDMI_74250 },
-	{ DIV_ROUND_UP(148500 * 1000, 1001), AUD_CONFIG_PIXEL_CLOCK_HDMI_148352 },
+	{ 148352, AUD_CONFIG_PIXEL_CLOCK_HDMI_148352 },
 	{ 148500, AUD_CONFIG_PIXEL_CLOCK_HDMI_148500 },
 };
 
 /* HDMI N/CTS table */
 #define TMDS_297M 297000
-#define TMDS_296M DIV_ROUND_UP(297000 * 1000, 1001)
+#define TMDS_296M 296703
 static const struct {
 	int sample_rate;
 	int clock;
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 68421c273c8c..ce82f9c7df24 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -1231,20 +1231,13 @@ static const struct dmi_system_id intel_no_opregion_vbt[] = {
 	{ }
 };
 
-static const struct bdb_header *validate_vbt(const void __iomem *_base,
+static const struct bdb_header *validate_vbt(const void *base,
 					     size_t size,
-					     const void __iomem *_vbt,
+					     const void *_vbt,
 					     const char *source)
 {
-	/*
-	 * This is the one place where we explicitly discard the address space
-	 * (__iomem) of the BIOS/VBT. (And this will cause a sparse complaint.)
-	 * From now on everything is based on 'base', and treated as regular
-	 * memory.
-	 */
-	const void *base = (const void *) _base;
-	size_t offset = _vbt - _base;
-	const struct vbt_header *vbt = base + offset;
+	size_t offset = _vbt - base;
+	const struct vbt_header *vbt = _vbt;
 	const struct bdb_header *bdb;
 
 	if (offset + sizeof(struct vbt_header) > size) {
@@ -1282,7 +1275,15 @@ static const struct bdb_header *find_vbt(void __iomem *bios, size_t size)
 	/* Scour memory looking for the VBT signature. */
 	for (i = 0; i + 4 < size; i++) {
 		if (ioread32(bios + i) == *((const u32 *) "$VBT")) {
-			bdb = validate_vbt(bios, size, bios + i, "PCI ROM");
+			/*
+			 * This is the one place where we explicitly discard the
+			 * address space (__iomem) of the BIOS/VBT. From now on
+			 * everything is based on 'base', and treated as regular
+			 * memory.
+			 */
+			void *_bios = (void __force *) bios;
+
+			bdb = validate_vbt(_bios, size, _bios + i, "PCI ROM");
 			break;
 		}
 	}
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index cddb0c692334..82128b95785c 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1157,12 +1157,10 @@ static const char *state_string(bool enabled)
 void assert_pll(struct drm_i915_private *dev_priv,
 		enum pipe pipe, bool state)
 {
-	int reg;
 	u32 val;
 	bool cur_state;
 
-	reg = DPLL(pipe);
-	val = I915_READ(reg);
+	val = I915_READ(DPLL(pipe));
 	cur_state = !!(val & DPLL_VCO_ENABLE);
 	I915_STATE_WARN(cur_state != state,
 	     "PLL state assertion failure (expected %s, current %s)\n",
@@ -1219,20 +1217,16 @@ void assert_shared_dpll(struct drm_i915_private *dev_priv,
 static void assert_fdi_tx(struct drm_i915_private *dev_priv,
 			  enum pipe pipe, bool state)
 {
-	int reg;
-	u32 val;
 	bool cur_state;
 	enum transcoder cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv,
 								      pipe);
 
 	if (HAS_DDI(dev_priv->dev)) {
 		/* DDI does not have a specific FDI_TX register */
-		reg = TRANS_DDI_FUNC_CTL(cpu_transcoder);
-		val = I915_READ(reg);
+		u32 val = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
 		cur_state = !!(val & TRANS_DDI_FUNC_ENABLE);
 	} else {
-		reg = FDI_TX_CTL(pipe);
-		val = I915_READ(reg);
+		u32 val = I915_READ(FDI_TX_CTL(pipe));
 		cur_state = !!(val & FDI_TX_ENABLE);
 	}
 	I915_STATE_WARN(cur_state != state,
@@ -1245,12 +1239,10 @@ static void assert_fdi_tx(struct drm_i915_private *dev_priv,
 static void assert_fdi_rx(struct drm_i915_private *dev_priv,
 			  enum pipe pipe, bool state)
 {
-	int reg;
 	u32 val;
 	bool cur_state;
 
-	reg = FDI_RX_CTL(pipe);
-	val = I915_READ(reg);
+	val = I915_READ(FDI_RX_CTL(pipe));
 	cur_state = !!(val & FDI_RX_ENABLE);
 	I915_STATE_WARN(cur_state != state,
 	     "FDI RX state assertion failure (expected %s, current %s)\n",
@@ -1262,7 +1254,6 @@ static void assert_fdi_rx(struct drm_i915_private *dev_priv,
 static void assert_fdi_tx_pll_enabled(struct drm_i915_private *dev_priv,
 				      enum pipe pipe)
 {
-	int reg;
 	u32 val;
 
 	/* ILK FDI PLL is always enabled */
@@ -1273,20 +1264,17 @@ static void assert_fdi_tx_pll_enabled(struct drm_i915_private *dev_priv,
 	if (HAS_DDI(dev_priv->dev))
 		return;
 
-	reg = FDI_TX_CTL(pipe);
-	val = I915_READ(reg);
+	val = I915_READ(FDI_TX_CTL(pipe));
 	I915_STATE_WARN(!(val & FDI_TX_PLL_ENABLE), "FDI TX PLL assertion failure, should be active but is disabled\n");
 }
 
 void assert_fdi_rx_pll(struct drm_i915_private *dev_priv,
 		       enum pipe pipe, bool state)
 {
-	int reg;
 	u32 val;
 	bool cur_state;
 
-	reg = FDI_RX_CTL(pipe);
-	val = I915_READ(reg);
+	val = I915_READ(FDI_RX_CTL(pipe));
 	cur_state = !!(val & FDI_RX_PLL_ENABLE);
 	I915_STATE_WARN(cur_state != state,
 	     "FDI RX PLL assertion failure (expected %s, current %s)\n",
@@ -1356,8 +1344,6 @@ static void assert_cursor(struct drm_i915_private *dev_priv,
 void assert_pipe(struct drm_i915_private *dev_priv,
 		 enum pipe pipe, bool state)
 {
-	int reg;
-	u32 val;
 	bool cur_state;
 	enum transcoder cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv,
 								      pipe);
@@ -1371,8 +1357,7 @@ void assert_pipe(struct drm_i915_private *dev_priv,
 				POWER_DOMAIN_TRANSCODER(cpu_transcoder))) {
 		cur_state = false;
 	} else {
-		reg = PIPECONF(cpu_transcoder);
-		val = I915_READ(reg);
+		u32 val = I915_READ(PIPECONF(cpu_transcoder));
 		cur_state = !!(val & PIPECONF_ENABLE);
 	}
 
@@ -1384,12 +1369,10 @@ void assert_pipe(struct drm_i915_private *dev_priv,
 static void assert_plane(struct drm_i915_private *dev_priv,
 			 enum plane plane, bool state)
 {
-	int reg;
 	u32 val;
 	bool cur_state;
 
-	reg = DSPCNTR(plane);
-	val = I915_READ(reg);
+	val = I915_READ(DSPCNTR(plane));
 	cur_state = !!(val & DISPLAY_PLANE_ENABLE);
 	I915_STATE_WARN(cur_state != state,
 	     "plane %c assertion failure (expected %s, current %s)\n",
@@ -1403,14 +1386,11 @@ static void assert_planes_disabled(struct drm_i915_private *dev_priv,
 				   enum pipe pipe)
 {
 	struct drm_device *dev = dev_priv->dev;
-	int reg, i;
-	u32 val;
-	int cur_pipe;
+	int i;
 
 	/* Primary planes are fixed to pipes on gen4+ */
 	if (INTEL_INFO(dev)->gen >= 4) {
-		reg = DSPCNTR(pipe);
-		val = I915_READ(reg);
+		u32 val = I915_READ(DSPCNTR(pipe));
 		I915_STATE_WARN(val & DISPLAY_PLANE_ENABLE,
 		     "plane %c assertion failure, should be disabled but not\n",
 		     plane_name(pipe));
@@ -1419,9 +1399,8 @@ static void assert_planes_disabled(struct drm_i915_private *dev_priv,
 
 	/* Need to check both planes against the pipe */
 	for_each_pipe(dev_priv, i) {
-		reg = DSPCNTR(i);
-		val = I915_READ(reg);
-		cur_pipe = (val & DISPPLANE_SEL_PIPE_MASK) >>
+		u32 val = I915_READ(DSPCNTR(i));
+		enum pipe cur_pipe = (val & DISPPLANE_SEL_PIPE_MASK) >>
 			DISPPLANE_SEL_PIPE_SHIFT;
 		I915_STATE_WARN((val & DISPLAY_PLANE_ENABLE) && pipe == cur_pipe,
 		     "plane %c assertion failure, should be off on pipe %c but is still active\n",
@@ -1433,33 +1412,29 @@ static void assert_sprites_disabled(struct drm_i915_private *dev_priv,
 				    enum pipe pipe)
 {
 	struct drm_device *dev = dev_priv->dev;
-	int reg, sprite;
-	u32 val;
+	int sprite;
 
 	if (INTEL_INFO(dev)->gen >= 9) {
 		for_each_sprite(dev_priv, pipe, sprite) {
-			val = I915_READ(PLANE_CTL(pipe, sprite));
+			u32 val = I915_READ(PLANE_CTL(pipe, sprite));
 			I915_STATE_WARN(val & PLANE_CTL_ENABLE,
 			     "plane %d assertion failure, should be off on pipe %c but is still active\n",
 			     sprite, pipe_name(pipe));
 		}
 	} else if (IS_VALLEYVIEW(dev)) {
 		for_each_sprite(dev_priv, pipe, sprite) {
-			reg = SPCNTR(pipe, sprite);
-			val = I915_READ(reg);
+			u32 val = I915_READ(SPCNTR(pipe, sprite));
 			I915_STATE_WARN(val & SP_ENABLE,
 			     "sprite %c assertion failure, should be off on pipe %c but is still active\n",
 			     sprite_name(pipe, sprite), pipe_name(pipe));
 		}
 	} else if (INTEL_INFO(dev)->gen >= 7) {
-		reg = SPRCTL(pipe);
-		val = I915_READ(reg);
+		u32 val = I915_READ(SPRCTL(pipe));
 		I915_STATE_WARN(val & SPRITE_ENABLE,
 		     "sprite %c assertion failure, should be off on pipe %c but is still active\n",
 		     plane_name(pipe), pipe_name(pipe));
 	} else if (INTEL_INFO(dev)->gen >= 5) {
-		reg = DVSCNTR(pipe);
-		val = I915_READ(reg);
+		u32 val = I915_READ(DVSCNTR(pipe));
 		I915_STATE_WARN(val & DVS_ENABLE,
 		     "sprite %c assertion failure, should be off on pipe %c but is still active\n",
 		     plane_name(pipe), pipe_name(pipe));
@@ -1488,12 +1463,10 @@ static void ibx_assert_pch_refclk_enabled(struct drm_i915_private *dev_priv)
 static void assert_pch_transcoder_disabled(struct drm_i915_private *dev_priv,
 					   enum pipe pipe)
 {
-	int reg;
 	u32 val;
 	bool enabled;
 
-	reg = PCH_TRANSCONF(pipe);
-	val = I915_READ(reg);
+	val = I915_READ(PCH_TRANSCONF(pipe));
 	enabled = !!(val & TRANS_ENABLE);
 	I915_STATE_WARN(enabled,
 	     "transcoder assertion failed, should be off on pipe %c but is still active\n",
@@ -1600,21 +1573,18 @@ static void assert_pch_hdmi_disabled(struct drm_i915_private *dev_priv,
 static void assert_pch_ports_disabled(struct drm_i915_private *dev_priv,
 				      enum pipe pipe)
 {
-	int reg;
 	u32 val;
 
 	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_B, TRANS_DP_PORT_SEL_B);
 	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_C, TRANS_DP_PORT_SEL_C);
 	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_D, TRANS_DP_PORT_SEL_D);
 
-	reg = PCH_ADPA;
-	val = I915_READ(reg);
+	val = I915_READ(PCH_ADPA);
 	I915_STATE_WARN(adpa_pipe_enabled(dev_priv, pipe, val),
 	     "PCH VGA enabled on transcoder %c, should be disabled\n",
 	     pipe_name(pipe));
 
-	reg = PCH_LVDS;
-	val = I915_READ(reg);
+	val = I915_READ(PCH_LVDS);
 	I915_STATE_WARN(lvds_pipe_enabled(dev_priv, pipe, val),
 	     "PCH LVDS enabled on transcoder %c, should be disabled\n",
 	     pipe_name(pipe));
@@ -4804,6 +4774,7 @@ static void intel_post_plane_update(struct intel_crtc *crtc)
 	struct intel_crtc_atomic_commit *atomic = &crtc->atomic;
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_plane *plane;
 
 	if (atomic->wait_vblank)
 		intel_wait_for_vblank(dev, crtc->pipe);
@@ -4822,6 +4793,10 @@ static void intel_post_plane_update(struct intel_crtc *crtc)
 	if (atomic->post_enable_primary)
 		intel_post_enable_primary(&crtc->base);
 
+	drm_for_each_plane_mask(plane, dev, atomic->update_sprite_watermarks)
+		intel_update_sprite_watermarks(plane, &crtc->base,
+					       0, 0, 0, false, false);
+
 	memset(atomic, 0, sizeof(*atomic));
 }
 
@@ -9952,7 +9927,7 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base)
 		}
 		cntl |= pipe << 28; /* Connect to correct pipe */
 
-		if (IS_HASWELL(dev) || IS_BROADWELL(dev))
+		if (HAS_DDI(dev))
 			cntl |= CURSOR_PIPE_CSC_ENABLE;
 	}
 
@@ -10822,7 +10797,7 @@ static bool page_flip_finished(struct intel_crtc *crtc)
 	 */
 	return (I915_READ(DSPSURFLIVE(crtc->plane)) & ~0xfff) ==
 		crtc->unpin_work->gtt_offset &&
-		g4x_flip_count_after_eq(I915_READ(PIPE_FLIPCOUNT_GM45(crtc->pipe)),
+		g4x_flip_count_after_eq(I915_READ(PIPE_FLIPCOUNT_G4X(crtc->pipe)),
 				    crtc->unpin_work->flip_count);
 }
 
@@ -10848,11 +10823,11 @@ void intel_prepare_page_flip(struct drm_device *dev, int plane)
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 }
 
-static inline void intel_mark_page_flip_active(struct intel_crtc *intel_crtc)
+static inline void intel_mark_page_flip_active(struct intel_unpin_work *work)
 {
 	/* Ensure that the work item is consistent when activating it ... */
 	smp_wmb();
-	atomic_set(&intel_crtc->unpin_work->pending, INTEL_FLIP_PENDING);
+	atomic_set(&work->pending, INTEL_FLIP_PENDING);
 	/* and that it is marked active as soon as the irq could fire. */
 	smp_wmb();
 }
@@ -10888,7 +10863,7 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset);
 	intel_ring_emit(ring, 0); /* aux display base address, unused */
 
-	intel_mark_page_flip_active(intel_crtc);
+	intel_mark_page_flip_active(intel_crtc->unpin_work);
 	return 0;
 }
 
@@ -10920,7 +10895,7 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset);
 	intel_ring_emit(ring, MI_NOOP);
 
-	intel_mark_page_flip_active(intel_crtc);
+	intel_mark_page_flip_active(intel_crtc->unpin_work);
 	return 0;
 }
 
@@ -10959,7 +10934,7 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
 	pipesrc = I915_READ(PIPESRC(intel_crtc->pipe)) & 0x0fff0fff;
 	intel_ring_emit(ring, pf | pipesrc);
 
-	intel_mark_page_flip_active(intel_crtc);
+	intel_mark_page_flip_active(intel_crtc->unpin_work);
 	return 0;
 }
 
@@ -10995,7 +10970,7 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
 	pipesrc = I915_READ(PIPESRC(intel_crtc->pipe)) & 0x0fff0fff;
 	intel_ring_emit(ring, pf | pipesrc);
 
-	intel_mark_page_flip_active(intel_crtc);
+	intel_mark_page_flip_active(intel_crtc->unpin_work);
 	return 0;
 }
 
@@ -11090,7 +11065,7 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset);
 	intel_ring_emit(ring, (MI_NOOP));
 
-	intel_mark_page_flip_active(intel_crtc);
+	intel_mark_page_flip_active(intel_crtc->unpin_work);
 	return 0;
 }
 
@@ -11121,7 +11096,8 @@ static bool use_mmio_flip(struct intel_engine_cs *ring,
 		return ring != i915_gem_request_get_ring(obj->last_write_req);
 }
 
-static void skl_do_mmio_flip(struct intel_crtc *intel_crtc)
+static void skl_do_mmio_flip(struct intel_crtc *intel_crtc,
+			     struct intel_unpin_work *work)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -11162,11 +11138,12 @@ static void skl_do_mmio_flip(struct intel_crtc *intel_crtc)
 	I915_WRITE(PLANE_CTL(pipe, 0), ctl);
 	I915_WRITE(PLANE_STRIDE(pipe, 0), stride);
 
-	I915_WRITE(PLANE_SURF(pipe, 0), intel_crtc->unpin_work->gtt_offset);
+	I915_WRITE(PLANE_SURF(pipe, 0), work->gtt_offset);
 	POSTING_READ(PLANE_SURF(pipe, 0));
 }
 
-static void ilk_do_mmio_flip(struct intel_crtc *intel_crtc)
+static void ilk_do_mmio_flip(struct intel_crtc *intel_crtc,
+			     struct intel_unpin_work *work)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -11186,31 +11163,36 @@ static void ilk_do_mmio_flip(struct intel_crtc *intel_crtc)
 
 	I915_WRITE(reg, dspcntr);
 
-	I915_WRITE(DSPSURF(intel_crtc->plane),
-		   intel_crtc->unpin_work->gtt_offset);
+	I915_WRITE(DSPSURF(intel_crtc->plane), work->gtt_offset);
 	POSTING_READ(DSPSURF(intel_crtc->plane));
-
 }
 
 /*
  * XXX: This is the temporary way to update the plane registers until we get
  * around to using the usual plane update functions for MMIO flips
  */
-static void intel_do_mmio_flip(struct intel_crtc *intel_crtc)
+static void intel_do_mmio_flip(struct intel_mmio_flip *mmio_flip)
 {
-	struct drm_device *dev = intel_crtc->base.dev;
+	struct intel_crtc *crtc = mmio_flip->crtc;
+	struct intel_unpin_work *work;
 
-	intel_mark_page_flip_active(intel_crtc);
+	spin_lock_irq(&crtc->base.dev->event_lock);
+	work = crtc->unpin_work;
+	spin_unlock_irq(&crtc->base.dev->event_lock);
+	if (work == NULL)
+		return;
 
-	intel_pipe_update_start(intel_crtc);
+	intel_mark_page_flip_active(work);
 
-	if (INTEL_INFO(dev)->gen >= 9)
-		skl_do_mmio_flip(intel_crtc);
+	intel_pipe_update_start(crtc);
+
+	if (INTEL_INFO(mmio_flip->i915)->gen >= 9)
+		skl_do_mmio_flip(crtc, work);
 	else
 		/* use_mmio_flip() retricts MMIO flips to ilk+ */
-		ilk_do_mmio_flip(intel_crtc);
+		ilk_do_mmio_flip(crtc, work);
 
-	intel_pipe_update_end(intel_crtc);
+	intel_pipe_update_end(crtc);
 }
 
 static void intel_mmio_flip_work_func(struct work_struct *work)
@@ -11218,15 +11200,15 @@ static void intel_mmio_flip_work_func(struct work_struct *work)
 	struct intel_mmio_flip *mmio_flip =
 		container_of(work, struct intel_mmio_flip, work);
 
-	if (mmio_flip->req)
+	if (mmio_flip->req) {
 		WARN_ON(__i915_wait_request(mmio_flip->req,
 					    mmio_flip->crtc->reset_counter,
 					    false, NULL,
 					    &mmio_flip->i915->rps.mmioflips));
+		i915_gem_request_unreference__unlocked(mmio_flip->req);
+	}
 
-	intel_do_mmio_flip(mmio_flip->crtc);
-
-	i915_gem_request_unreference__unlocked(mmio_flip->req);
+	intel_do_mmio_flip(mmio_flip);
 	kfree(mmio_flip);
 }
 
@@ -11427,7 +11409,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	intel_crtc->reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter);
 
 	if (INTEL_INFO(dev)->gen >= 5 || IS_G4X(dev))
-		work->flip_count = I915_READ(PIPE_FLIPCOUNT_GM45(pipe)) + 1;
+		work->flip_count = I915_READ(PIPE_FLIPCOUNT_G4X(pipe)) + 1;
 
 	if (IS_VALLEYVIEW(dev)) {
 		ring = &dev_priv->ring[BCS];
@@ -11577,30 +11559,16 @@ retry:
 static bool intel_wm_need_update(struct drm_plane *plane,
 				 struct drm_plane_state *state)
 {
-	struct intel_plane_state *new = to_intel_plane_state(state);
-	struct intel_plane_state *cur = to_intel_plane_state(plane->state);
-
-	/* Update watermarks on tiling or size changes. */
+	/* Update watermarks on tiling changes. */
 	if (!plane->state->fb || !state->fb ||
 	    plane->state->fb->modifier[0] != state->fb->modifier[0] ||
-	    plane->state->rotation != state->rotation ||
-	    drm_rect_width(&new->src) != drm_rect_width(&cur->src) ||
-	    drm_rect_height(&new->src) != drm_rect_height(&cur->src) ||
-	    drm_rect_width(&new->dst) != drm_rect_width(&cur->dst) ||
-	    drm_rect_height(&new->dst) != drm_rect_height(&cur->dst))
+	    plane->state->rotation != state->rotation)
 		return true;
 
-	return false;
-}
-
-static bool needs_scaling(struct intel_plane_state *state)
-{
-	int src_w = drm_rect_width(&state->src) >> 16;
-	int src_h = drm_rect_height(&state->src) >> 16;
-	int dst_w = drm_rect_width(&state->dst);
-	int dst_h = drm_rect_height(&state->dst);
+	if (plane->state->crtc_w != state->crtc_w)
+		return true;
 
-	return (src_w != dst_w || src_h != dst_h);
+	return false;
 }
 
 int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state,
@@ -11618,6 +11586,7 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state,
 	bool mode_changed = needs_modeset(crtc_state);
 	bool was_crtc_enabled = crtc->state->active;
 	bool is_crtc_enabled = crtc_state->active;
+
 	bool turn_off, turn_on, visible, was_visible;
 	struct drm_framebuffer *fb = plane_state->fb;
 
@@ -11735,23 +11704,11 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state,
 	case DRM_PLANE_TYPE_CURSOR:
 		break;
 	case DRM_PLANE_TYPE_OVERLAY:
-		/*
-		 * WaCxSRDisabledForSpriteScaling:ivb
-		 *
-		 * cstate->update_wm was already set above, so this flag will
-		 * take effect when we commit and program watermarks.
-		 */
-		if (IS_IVYBRIDGE(dev) &&
-		    needs_scaling(to_intel_plane_state(plane_state)) &&
-		    !needs_scaling(old_plane_state)) {
-			to_intel_crtc_state(crtc_state)->disable_lp_wm = true;
-		} else if (turn_off && !mode_changed) {
+		if (turn_off && !mode_changed) {
 			intel_crtc->atomic.wait_vblank = true;
 			intel_crtc->atomic.update_sprite_watermarks |=
 				1 << i;
 		}
-
-		break;
 	}
 	return 0;
 }
@@ -14942,13 +14899,12 @@ intel_check_plane_mapping(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 reg, val;
+	u32 val;
 
 	if (INTEL_INFO(dev)->num_pipes == 1)
 		return true;
 
-	reg = DSPCNTR(!crtc->plane);
-	val = I915_READ(reg);
+	val = I915_READ(DSPCNTR(!crtc->plane));
 
 	if ((val & DISPLAY_PLANE_ENABLE) &&
 	    (!!(val & DISPPLANE_SEL_PIPE_MASK) == crtc->pipe))
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 18bcfbe0b8ba..09bdd94ca3ba 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -574,8 +574,6 @@ static int edp_notify_handler(struct notifier_block *this, unsigned long code,
 						 edp_notifier);
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 pp_div;
-	u32 pp_ctrl_reg, pp_div_reg;
 
 	if (!is_edp(intel_dp) || code != SYS_RESTART)
 		return 0;
@@ -584,6 +582,8 @@ static int edp_notify_handler(struct notifier_block *this, unsigned long code,
 
 	if (IS_VALLEYVIEW(dev)) {
 		enum pipe pipe = vlv_power_sequencer_pipe(intel_dp);
+		u32 pp_ctrl_reg, pp_div_reg;
+		u32 pp_div;
 
 		pp_ctrl_reg = VLV_PIPE_PP_CONTROL(pipe);
 		pp_div_reg  = VLV_PIPE_PP_DIVISOR(pipe);
@@ -5536,7 +5536,6 @@ static void intel_dp_set_drrs_state(struct drm_device *dev, int refresh_rate)
 	struct intel_dp *intel_dp = dev_priv->drrs.dp;
 	struct intel_crtc_state *config = NULL;
 	struct intel_crtc *intel_crtc = NULL;
-	u32 reg, val;
 	enum drrs_refresh_rate_type index = DRRS_HIGH_RR;
 
 	if (refresh_rate <= 0) {
@@ -5598,9 +5597,10 @@ static void intel_dp_set_drrs_state(struct drm_device *dev, int refresh_rate)
 			DRM_ERROR("Unsupported refreshrate type\n");
 		}
 	} else if (INTEL_INFO(dev)->gen > 6) {
-		reg = PIPECONF(intel_crtc->config->cpu_transcoder);
-		val = I915_READ(reg);
+		u32 reg = PIPECONF(intel_crtc->config->cpu_transcoder);
+		u32 val;
 
+		val = I915_READ(reg);
 		if (index > DRRS_HIGH_RR) {
 			if (IS_VALLEYVIEW(dev))
 				val |= PIPECONF_EDP_RR_MODE_SWITCH_VLV;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 91b6b4060333..0598932ce623 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -468,9 +468,6 @@ struct intel_crtc_state {
 
 	/* w/a for waiting 2 vblanks during crtc enable */
 	enum pipe hsw_workaround_pipe;
-
-	/* IVB sprite scaling w/a (WaCxSRDisabledForSpriteScaling:ivb) */
-	bool disable_lp_wm;
 };
 
 struct vlv_wm_state {
@@ -1399,6 +1396,12 @@ void intel_init_clock_gating(struct drm_device *dev);
 void intel_suspend_hw(struct drm_device *dev);
 int ilk_wm_max_level(const struct drm_device *dev);
 void intel_update_watermarks(struct drm_crtc *crtc);
+void intel_update_sprite_watermarks(struct drm_plane *plane,
+				    struct drm_crtc *crtc,
+				    uint32_t sprite_width,
+				    uint32_t sprite_height,
+				    int pixel_size,
+				    bool enabled, bool scaled);
 void intel_init_pm(struct drm_device *dev);
 void intel_pm_setup(struct drm_device *dev);
 void intel_gpu_ips_init(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 3b28ed3237d3..9eafa191cee2 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -113,17 +113,18 @@ static u32 hsw_infoframe_enable(enum hdmi_infoframe_type type)
 	}
 }
 
-static u32 hsw_infoframe_data_reg(enum hdmi_infoframe_type type,
-				  enum transcoder cpu_transcoder,
-				  struct drm_i915_private *dev_priv)
+static u32 hsw_dip_data_reg(struct drm_i915_private *dev_priv,
+			    enum transcoder cpu_transcoder,
+			    enum hdmi_infoframe_type type,
+			    int i)
 {
 	switch (type) {
 	case HDMI_INFOFRAME_TYPE_AVI:
-		return HSW_TVIDEO_DIP_AVI_DATA(cpu_transcoder);
+		return HSW_TVIDEO_DIP_AVI_DATA(cpu_transcoder, i);
 	case HDMI_INFOFRAME_TYPE_SPD:
-		return HSW_TVIDEO_DIP_SPD_DATA(cpu_transcoder);
+		return HSW_TVIDEO_DIP_SPD_DATA(cpu_transcoder, i);
 	case HDMI_INFOFRAME_TYPE_VENDOR:
-		return HSW_TVIDEO_DIP_VS_DATA(cpu_transcoder);
+		return HSW_TVIDEO_DIP_VS_DATA(cpu_transcoder, i);
 	default:
 		DRM_DEBUG_DRIVER("unknown info frame type %d\n", type);
 		return 0;
@@ -365,14 +366,13 @@ static void hsw_write_infoframe(struct drm_encoder *encoder,
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
-	u32 ctl_reg = HSW_TVIDEO_DIP_CTL(intel_crtc->config->cpu_transcoder);
+	enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
+	u32 ctl_reg = HSW_TVIDEO_DIP_CTL(cpu_transcoder);
 	u32 data_reg;
 	int i;
 	u32 val = I915_READ(ctl_reg);
 
-	data_reg = hsw_infoframe_data_reg(type,
-					  intel_crtc->config->cpu_transcoder,
-					  dev_priv);
+	data_reg = hsw_dip_data_reg(dev_priv, cpu_transcoder, type, 0);
 	if (data_reg == 0)
 		return;
 
@@ -381,12 +381,14 @@ static void hsw_write_infoframe(struct drm_encoder *encoder,
 
 	mmiowb();
 	for (i = 0; i < len; i += 4) {
-		I915_WRITE(data_reg + i, *data);
+		I915_WRITE(hsw_dip_data_reg(dev_priv, cpu_transcoder,
+					    type, i >> 2), *data);
 		data++;
 	}
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
-		I915_WRITE(data_reg + i, 0);
+		I915_WRITE(hsw_dip_data_reg(dev_priv, cpu_transcoder,
+					    type, i >> 2), 0);
 	mmiowb();
 
 	val |= hsw_infoframe_enable(type);
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index a64f26c670af..1369fc41d039 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -114,8 +114,8 @@ intel_i2c_reset(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	I915_WRITE(dev_priv->gpio_mmio_base + GMBUS0, 0);
-	I915_WRITE(dev_priv->gpio_mmio_base + GMBUS4, 0);
+	I915_WRITE(GMBUS0, 0);
+	I915_WRITE(GMBUS4, 0);
 }
 
 static void intel_i2c_quirk_set(struct drm_i915_private *dev_priv, bool enable)
@@ -261,7 +261,6 @@ gmbus_wait_hw_status(struct drm_i915_private *dev_priv,
 		     u32 gmbus4_irq_en)
 {
 	int i;
-	int reg_offset = dev_priv->gpio_mmio_base;
 	u32 gmbus2 = 0;
 	DEFINE_WAIT(wait);
 
@@ -271,13 +270,13 @@ gmbus_wait_hw_status(struct drm_i915_private *dev_priv,
 	/* Important: The hw handles only the first bit, so set only one! Since
 	 * we also need to check for NAKs besides the hw ready/idle signal, we
 	 * need to wake up periodically and check that ourselves. */
-	I915_WRITE(GMBUS4 + reg_offset, gmbus4_irq_en);
+	I915_WRITE(GMBUS4, gmbus4_irq_en);
 
 	for (i = 0; i < msecs_to_jiffies_timeout(50); i++) {
 		prepare_to_wait(&dev_priv->gmbus_wait_queue, &wait,
 				TASK_UNINTERRUPTIBLE);
 
-		gmbus2 = I915_READ_NOTRACE(GMBUS2 + reg_offset);
+		gmbus2 = I915_READ_NOTRACE(GMBUS2);
 		if (gmbus2 & (GMBUS_SATOER | gmbus2_status))
 			break;
 
@@ -285,7 +284,7 @@ gmbus_wait_hw_status(struct drm_i915_private *dev_priv,
 	}
 	finish_wait(&dev_priv->gmbus_wait_queue, &wait);
 
-	I915_WRITE(GMBUS4 + reg_offset, 0);
+	I915_WRITE(GMBUS4, 0);
 
 	if (gmbus2 & GMBUS_SATOER)
 		return -ENXIO;
@@ -298,20 +297,19 @@ static int
 gmbus_wait_idle(struct drm_i915_private *dev_priv)
 {
 	int ret;
-	int reg_offset = dev_priv->gpio_mmio_base;
 
-#define C ((I915_READ_NOTRACE(GMBUS2 + reg_offset) & GMBUS_ACTIVE) == 0)
+#define C ((I915_READ_NOTRACE(GMBUS2) & GMBUS_ACTIVE) == 0)
 
 	if (!HAS_GMBUS_IRQ(dev_priv->dev))
 		return wait_for(C, 10);
 
 	/* Important: The hw handles only the first bit, so set only one! */
-	I915_WRITE(GMBUS4 + reg_offset, GMBUS_IDLE_EN);
+	I915_WRITE(GMBUS4, GMBUS_IDLE_EN);
 
 	ret = wait_event_timeout(dev_priv->gmbus_wait_queue, C,
 				 msecs_to_jiffies_timeout(10));
 
-	I915_WRITE(GMBUS4 + reg_offset, 0);
+	I915_WRITE(GMBUS4, 0);
 
 	if (ret)
 		return 0;
@@ -325,9 +323,7 @@ gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv,
 		      unsigned short addr, u8 *buf, unsigned int len,
 		      u32 gmbus1_index)
 {
-	int reg_offset = dev_priv->gpio_mmio_base;
-
-	I915_WRITE(GMBUS1 + reg_offset,
+	I915_WRITE(GMBUS1,
 		   gmbus1_index |
 		   GMBUS_CYCLE_WAIT |
 		   (len << GMBUS_BYTE_COUNT_SHIFT) |
@@ -342,7 +338,7 @@ gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv,
 		if (ret)
 			return ret;
 
-		val = I915_READ(GMBUS3 + reg_offset);
+		val = I915_READ(GMBUS3);
 		do {
 			*buf++ = val & 0xff;
 			val >>= 8;
@@ -380,7 +376,6 @@ static int
 gmbus_xfer_write_chunk(struct drm_i915_private *dev_priv,
 		       unsigned short addr, u8 *buf, unsigned int len)
 {
-	int reg_offset = dev_priv->gpio_mmio_base;
 	unsigned int chunk_size = len;
 	u32 val, loop;
 
@@ -390,8 +385,8 @@ gmbus_xfer_write_chunk(struct drm_i915_private *dev_priv,
 		len -= 1;
 	}
 
-	I915_WRITE(GMBUS3 + reg_offset, val);
-	I915_WRITE(GMBUS1 + reg_offset,
+	I915_WRITE(GMBUS3, val);
+	I915_WRITE(GMBUS1,
 		   GMBUS_CYCLE_WAIT |
 		   (chunk_size << GMBUS_BYTE_COUNT_SHIFT) |
 		   (addr << GMBUS_SLAVE_ADDR_SHIFT) |
@@ -404,7 +399,7 @@ gmbus_xfer_write_chunk(struct drm_i915_private *dev_priv,
 			val |= *buf++ << (8 * loop);
 		} while (--len && ++loop < 4);
 
-		I915_WRITE(GMBUS3 + reg_offset, val);
+		I915_WRITE(GMBUS3, val);
 
 		ret = gmbus_wait_hw_status(dev_priv, GMBUS_HW_RDY,
 					   GMBUS_HW_RDY_EN);
@@ -452,7 +447,6 @@ gmbus_is_index_read(struct i2c_msg *msgs, int i, int num)
 static int
 gmbus_xfer_index_read(struct drm_i915_private *dev_priv, struct i2c_msg *msgs)
 {
-	int reg_offset = dev_priv->gpio_mmio_base;
 	u32 gmbus1_index = 0;
 	u32 gmbus5 = 0;
 	int ret;
@@ -466,13 +460,13 @@ gmbus_xfer_index_read(struct drm_i915_private *dev_priv, struct i2c_msg *msgs)
 
 	/* GMBUS5 holds 16-bit index */
 	if (gmbus5)
-		I915_WRITE(GMBUS5 + reg_offset, gmbus5);
+		I915_WRITE(GMBUS5, gmbus5);
 
 	ret = gmbus_xfer_read(dev_priv, &msgs[1], gmbus1_index);
 
 	/* Clear GMBUS5 after each index transfer */
 	if (gmbus5)
-		I915_WRITE(GMBUS5 + reg_offset, 0);
+		I915_WRITE(GMBUS5, 0);
 
 	return ret;
 }
@@ -486,7 +480,7 @@ gmbus_xfer(struct i2c_adapter *adapter,
 					       struct intel_gmbus,
 					       adapter);
 	struct drm_i915_private *dev_priv = bus->dev_priv;
-	int i = 0, inc, try = 0, reg_offset;
+	int i = 0, inc, try = 0;
 	int ret = 0;
 
 	intel_aux_display_runtime_get(dev_priv);
@@ -497,10 +491,8 @@ gmbus_xfer(struct i2c_adapter *adapter,
 		goto out;
 	}
 
-	reg_offset = dev_priv->gpio_mmio_base;
-
 retry:
-	I915_WRITE(GMBUS0 + reg_offset, bus->reg0);
+	I915_WRITE(GMBUS0, bus->reg0);
 
 	for (; i < num; i += inc) {
 		inc = 1;
@@ -530,7 +522,7 @@ retry:
 	 * a STOP on the very first cycle. To simplify the code we
 	 * unconditionally generate the STOP condition with an additional gmbus
 	 * cycle. */
-	I915_WRITE(GMBUS1 + reg_offset, GMBUS_CYCLE_STOP | GMBUS_SW_RDY);
+	I915_WRITE(GMBUS1, GMBUS_CYCLE_STOP | GMBUS_SW_RDY);
 
 	/* Mark the GMBUS interface as disabled after waiting for idle.
 	 * We will re-enable it at the start of the next xfer,
@@ -541,7 +533,7 @@ retry:
 			 adapter->name);
 		ret = -ETIMEDOUT;
 	}
-	I915_WRITE(GMBUS0 + reg_offset, 0);
+	I915_WRITE(GMBUS0, 0);
 	ret = ret ?: i;
 	goto out;
 
@@ -570,9 +562,9 @@ clear_err:
 	 * of resetting the GMBUS controller and so clearing the
 	 * BUS_ERROR raised by the slave's NAK.
 	 */
-	I915_WRITE(GMBUS1 + reg_offset, GMBUS_SW_CLR_INT);
-	I915_WRITE(GMBUS1 + reg_offset, 0);
-	I915_WRITE(GMBUS0 + reg_offset, 0);
+	I915_WRITE(GMBUS1, GMBUS_SW_CLR_INT);
+	I915_WRITE(GMBUS1, 0);
+	I915_WRITE(GMBUS0, 0);
 
 	DRM_DEBUG_KMS("GMBUS [%s] NAK for addr: %04x %c(%d)\n",
 			 adapter->name, msgs[i].addr,
@@ -595,7 +587,7 @@ clear_err:
 timeout:
 	DRM_INFO("GMBUS [%s] timed out, falling back to bit banging on pin %d\n",
 		 bus->adapter.name, bus->reg0 & 0xff);
-	I915_WRITE(GMBUS0 + reg_offset, 0);
+	I915_WRITE(GMBUS0, 0);
 
 	/* Hardware may not support GMBUS over these pins? Try GPIO bitbanging instead. */
 	bus->force_bit = 1;
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 5e70acf944c3..7f39b8ad88ae 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -98,15 +98,11 @@ static void intel_lvds_get_config(struct intel_encoder *encoder,
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 lvds_reg, tmp, flags = 0;
+	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
+	u32 tmp, flags = 0;
 	int dotclock;
 
-	if (HAS_PCH_SPLIT(dev))
-		lvds_reg = PCH_LVDS;
-	else
-		lvds_reg = LVDS;
-
-	tmp = I915_READ(lvds_reg);
+	tmp = I915_READ(lvds_encoder->reg);
 	if (tmp & LVDS_HSYNC_POLARITY)
 		flags |= DRM_MODE_FLAG_NHSYNC;
 	else
@@ -943,6 +939,7 @@ void intel_lvds_init(struct drm_device *dev)
 	struct drm_display_mode *downclock_mode = NULL;
 	struct edid *edid;
 	struct drm_crtc *crtc;
+	u32 lvds_reg;
 	u32 lvds;
 	int pipe;
 	u8 pin;
@@ -965,8 +962,15 @@ void intel_lvds_init(struct drm_device *dev)
 	if (dmi_check_system(intel_no_lvds))
 		return;
 
+	if (HAS_PCH_SPLIT(dev))
+		lvds_reg = PCH_LVDS;
+	else
+		lvds_reg = LVDS;
+
+	lvds = I915_READ(lvds_reg);
+
 	if (HAS_PCH_SPLIT(dev)) {
-		if ((I915_READ(PCH_LVDS) & LVDS_DETECTED) == 0)
+		if ((lvds & LVDS_DETECTED) == 0)
 			return;
 		if (dev_priv->vbt.edp_support) {
 			DRM_DEBUG_KMS("disable LVDS for eDP support\n");
@@ -976,8 +980,7 @@ void intel_lvds_init(struct drm_device *dev)
 
 	pin = GMBUS_PIN_PANEL;
 	if (!lvds_is_present_in_vbt(dev, &pin)) {
-		u32 reg = HAS_PCH_SPLIT(dev) ? PCH_LVDS : LVDS;
-		if ((I915_READ(reg) & LVDS_PORT_EN) == 0) {
+		if ((lvds & LVDS_PORT_EN) == 0) {
 			DRM_DEBUG_KMS("LVDS is not present in VBT\n");
 			return;
 		}
@@ -1054,11 +1057,7 @@ void intel_lvds_init(struct drm_device *dev)
 	connector->interlace_allowed = false;
 	connector->doublescan_allowed = false;
 
-	if (HAS_PCH_SPLIT(dev)) {
-		lvds_encoder->reg = PCH_LVDS;
-	} else {
-		lvds_encoder->reg = LVDS;
-	}
+	lvds_encoder->reg = lvds_reg;
 
 	/* create the scaling mode property */
 	drm_mode_create_scaling_mode_property(dev);
@@ -1139,7 +1138,6 @@ void intel_lvds_init(struct drm_device *dev)
 	if (HAS_PCH_SPLIT(dev))
 		goto failed;
 
-	lvds = I915_READ(LVDS);
 	pipe = (lvds & LVDS_PIPEB_SELECT) ? 1 : 0;
 	crtc = intel_get_crtc_for_pipe(dev, pipe);
 
diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c
index b706b4e750da..6dc13c02c28e 100644
--- a/drivers/gpu/drm/i915/intel_opregion.c
+++ b/drivers/gpu/drm/i915/intel_opregion.c
@@ -239,7 +239,7 @@ struct opregion_asle {
 static int swsci(struct drm_device *dev, u32 function, u32 parm, u32 *parm_out)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct opregion_swsci __iomem *swsci = dev_priv->opregion.swsci;
+	struct opregion_swsci *swsci = dev_priv->opregion.swsci;
 	u32 main_function, sub_function, scic;
 	u16 pci_swsci;
 	u32 dslp;
@@ -264,7 +264,7 @@ static int swsci(struct drm_device *dev, u32 function, u32 parm, u32 *parm_out)
 	}
 
 	/* Driver sleep timeout in ms. */
-	dslp = ioread32(&swsci->dslp);
+	dslp = swsci->dslp;
 	if (!dslp) {
 		/* The spec says 2ms should be the default, but it's too small
 		 * for some machines. */
@@ -277,7 +277,7 @@ static int swsci(struct drm_device *dev, u32 function, u32 parm, u32 *parm_out)
 	}
 
 	/* The spec tells us to do this, but we are the only user... */
-	scic = ioread32(&swsci->scic);
+	scic = swsci->scic;
 	if (scic & SWSCI_SCIC_INDICATOR) {
 		DRM_DEBUG_DRIVER("SWSCI request already in progress\n");
 		return -EBUSY;
@@ -285,8 +285,8 @@ static int swsci(struct drm_device *dev, u32 function, u32 parm, u32 *parm_out)
 
 	scic = function | SWSCI_SCIC_INDICATOR;
 
-	iowrite32(parm, &swsci->parm);
-	iowrite32(scic, &swsci->scic);
+	swsci->parm = parm;
+	swsci->scic = scic;
 
 	/* Ensure SCI event is selected and event trigger is cleared. */
 	pci_read_config_word(dev->pdev, PCI_SWSCI, &pci_swsci);
@@ -301,7 +301,7 @@ static int swsci(struct drm_device *dev, u32 function, u32 parm, u32 *parm_out)
 	pci_write_config_word(dev->pdev, PCI_SWSCI, pci_swsci);
 
 	/* Poll for the result. */
-#define C (((scic = ioread32(&swsci->scic)) & SWSCI_SCIC_INDICATOR) == 0)
+#define C (((scic = swsci->scic) & SWSCI_SCIC_INDICATOR) == 0)
 	if (wait_for(C, dslp)) {
 		DRM_DEBUG_DRIVER("SWSCI request timed out\n");
 		return -ETIMEDOUT;
@@ -317,7 +317,7 @@ static int swsci(struct drm_device *dev, u32 function, u32 parm, u32 *parm_out)
 	}
 
 	if (parm_out)
-		*parm_out = ioread32(&swsci->parm);
+		*parm_out = swsci->parm;
 
 	return 0;
 
@@ -412,7 +412,7 @@ static u32 asle_set_backlight(struct drm_device *dev, u32 bclp)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_connector *intel_connector;
-	struct opregion_asle __iomem *asle = dev_priv->opregion.asle;
+	struct opregion_asle *asle = dev_priv->opregion.asle;
 
 	DRM_DEBUG_DRIVER("bclp = 0x%08x\n", bclp);
 
@@ -437,7 +437,7 @@ static u32 asle_set_backlight(struct drm_device *dev, u32 bclp)
 	DRM_DEBUG_KMS("updating opregion backlight %d/255\n", bclp);
 	list_for_each_entry(intel_connector, &dev->mode_config.connector_list, base.head)
 		intel_panel_set_backlight_acpi(intel_connector, bclp, 255);
-	iowrite32(DIV_ROUND_UP(bclp * 100, 255) | ASLE_CBLV_VALID, &asle->cblv);
+	asle->cblv = DIV_ROUND_UP(bclp * 100, 255) | ASLE_CBLV_VALID;
 
 	drm_modeset_unlock(&dev->mode_config.connection_mutex);
 
@@ -524,14 +524,14 @@ static void asle_work(struct work_struct *work)
 	struct drm_i915_private *dev_priv =
 		container_of(opregion, struct drm_i915_private, opregion);
 	struct drm_device *dev = dev_priv->dev;
-	struct opregion_asle __iomem *asle = dev_priv->opregion.asle;
+	struct opregion_asle *asle = dev_priv->opregion.asle;
 	u32 aslc_stat = 0;
 	u32 aslc_req;
 
 	if (!asle)
 		return;
 
-	aslc_req = ioread32(&asle->aslc);
+	aslc_req = asle->aslc;
 
 	if (!(aslc_req & ASLC_REQ_MSK)) {
 		DRM_DEBUG_DRIVER("No request on ASLC interrupt 0x%08x\n",
@@ -540,34 +540,34 @@ static void asle_work(struct work_struct *work)
 	}
 
 	if (aslc_req & ASLC_SET_ALS_ILLUM)
-		aslc_stat |= asle_set_als_illum(dev, ioread32(&asle->alsi));
+		aslc_stat |= asle_set_als_illum(dev, asle->alsi);
 
 	if (aslc_req & ASLC_SET_BACKLIGHT)
-		aslc_stat |= asle_set_backlight(dev, ioread32(&asle->bclp));
+		aslc_stat |= asle_set_backlight(dev, asle->bclp);
 
 	if (aslc_req & ASLC_SET_PFIT)
-		aslc_stat |= asle_set_pfit(dev, ioread32(&asle->pfit));
+		aslc_stat |= asle_set_pfit(dev, asle->pfit);
 
 	if (aslc_req & ASLC_SET_PWM_FREQ)
-		aslc_stat |= asle_set_pwm_freq(dev, ioread32(&asle->pfmb));
+		aslc_stat |= asle_set_pwm_freq(dev, asle->pfmb);
 
 	if (aslc_req & ASLC_SUPPORTED_ROTATION_ANGLES)
 		aslc_stat |= asle_set_supported_rotation_angles(dev,
-							ioread32(&asle->srot));
+							asle->srot);
 
 	if (aslc_req & ASLC_BUTTON_ARRAY)
-		aslc_stat |= asle_set_button_array(dev, ioread32(&asle->iuer));
+		aslc_stat |= asle_set_button_array(dev, asle->iuer);
 
 	if (aslc_req & ASLC_CONVERTIBLE_INDICATOR)
-		aslc_stat |= asle_set_convertible(dev, ioread32(&asle->iuer));
+		aslc_stat |= asle_set_convertible(dev, asle->iuer);
 
 	if (aslc_req & ASLC_DOCKING_INDICATOR)
-		aslc_stat |= asle_set_docking(dev, ioread32(&asle->iuer));
+		aslc_stat |= asle_set_docking(dev, asle->iuer);
 
 	if (aslc_req & ASLC_ISCT_STATE_CHANGE)
 		aslc_stat |= asle_isct_state(dev);
 
-	iowrite32(aslc_stat, &asle->aslc);
+	asle->aslc = aslc_stat;
 }
 
 void intel_opregion_asle_intr(struct drm_device *dev)
@@ -592,8 +592,8 @@ static int intel_opregion_video_event(struct notifier_block *nb,
 	   Linux, these are handled by the dock, button and video drivers.
 	*/
 
-	struct opregion_acpi __iomem *acpi;
 	struct acpi_bus_event *event = data;
+	struct opregion_acpi *acpi;
 	int ret = NOTIFY_OK;
 
 	if (strcmp(event->device_class, ACPI_VIDEO_CLASS) != 0)
@@ -604,11 +604,10 @@ static int intel_opregion_video_event(struct notifier_block *nb,
 
 	acpi = system_opregion->acpi;
 
-	if (event->type == 0x80 &&
-	    (ioread32(&acpi->cevt) & 1) == 0)
+	if (event->type == 0x80 && ((acpi->cevt & 1) == 0))
 		ret = NOTIFY_BAD;
 
-	iowrite32(0, &acpi->csts);
+	acpi->csts = 0;
 
 	return ret;
 }
@@ -628,14 +627,14 @@ static u32 get_did(struct intel_opregion *opregion, int i)
 	u32 did;
 
 	if (i < ARRAY_SIZE(opregion->acpi->didl)) {
-		did = ioread32(&opregion->acpi->didl[i]);
+		did = opregion->acpi->didl[i];
 	} else {
 		i -= ARRAY_SIZE(opregion->acpi->didl);
 
 		if (WARN_ON(i >= ARRAY_SIZE(opregion->acpi->did2)))
 			return 0;
 
-		did = ioread32(&opregion->acpi->did2[i]);
+		did = opregion->acpi->did2[i];
 	}
 
 	return did;
@@ -644,14 +643,14 @@ static u32 get_did(struct intel_opregion *opregion, int i)
 static void set_did(struct intel_opregion *opregion, int i, u32 val)
 {
 	if (i < ARRAY_SIZE(opregion->acpi->didl)) {
-		iowrite32(val, &opregion->acpi->didl[i]);
+		opregion->acpi->didl[i] = val;
 	} else {
 		i -= ARRAY_SIZE(opregion->acpi->didl);
 
 		if (WARN_ON(i >= ARRAY_SIZE(opregion->acpi->did2)))
 			return;
 
-		iowrite32(val, &opregion->acpi->did2[i]);
+		opregion->acpi->did2[i] = val;
 	}
 }
 
@@ -773,7 +772,7 @@ static void intel_setup_cadls(struct drm_device *dev)
 	 * there are less than eight devices. */
 	do {
 		disp_id = get_did(opregion, i);
-		iowrite32(disp_id, &opregion->acpi->cadl[i]);
+		opregion->acpi->cadl[i] = disp_id;
 	} while (++i < 8 && disp_id != 0);
 }
 
@@ -792,16 +791,16 @@ void intel_opregion_init(struct drm_device *dev)
 		/* Notify BIOS we are ready to handle ACPI video ext notifs.
 		 * Right now, all the events are handled by the ACPI video module.
 		 * We don't actually need to do anything with them. */
-		iowrite32(0, &opregion->acpi->csts);
-		iowrite32(1, &opregion->acpi->drdy);
+		opregion->acpi->csts = 0;
+		opregion->acpi->drdy = 1;
 
 		system_opregion = opregion;
 		register_acpi_notifier(&intel_opregion_notifier);
 	}
 
 	if (opregion->asle) {
-		iowrite32(ASLE_TCHE_BLC_EN, &opregion->asle->tche);
-		iowrite32(ASLE_ARDY_READY, &opregion->asle->ardy);
+		opregion->asle->tche = ASLE_TCHE_BLC_EN;
+		opregion->asle->ardy = ASLE_ARDY_READY;
 	}
 }
 
@@ -814,19 +813,19 @@ void intel_opregion_fini(struct drm_device *dev)
 		return;
 
 	if (opregion->asle)
-		iowrite32(ASLE_ARDY_NOT_READY, &opregion->asle->ardy);
+		opregion->asle->ardy = ASLE_ARDY_NOT_READY;
 
 	cancel_work_sync(&dev_priv->opregion.asle_work);
 
 	if (opregion->acpi) {
-		iowrite32(0, &opregion->acpi->drdy);
+		opregion->acpi->drdy = 0;
 
 		system_opregion = NULL;
 		unregister_acpi_notifier(&intel_opregion_notifier);
 	}
 
 	/* just clear all opregion memory pointers now */
-	iounmap(opregion->header);
+	memunmap(opregion->header);
 	opregion->header = NULL;
 	opregion->acpi = NULL;
 	opregion->swsci = NULL;
@@ -899,10 +898,10 @@ int intel_opregion_setup(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_opregion *opregion = &dev_priv->opregion;
-	void __iomem *base;
 	u32 asls, mboxes;
 	char buf[sizeof(OPREGION_SIGNATURE)];
 	int err = 0;
+	void *base;
 
 	BUILD_BUG_ON(sizeof(struct opregion_header) != 0x100);
 	BUILD_BUG_ON(sizeof(struct opregion_acpi) != 0x100);
@@ -920,11 +919,11 @@ int intel_opregion_setup(struct drm_device *dev)
 	INIT_WORK(&opregion->asle_work, asle_work);
 #endif
 
-	base = acpi_os_ioremap(asls, OPREGION_SIZE);
+	base = memremap(asls, OPREGION_SIZE, MEMREMAP_WB);
 	if (!base)
 		return -ENOMEM;
 
-	memcpy_fromio(buf, base, sizeof(buf));
+	memcpy(buf, base, sizeof(buf));
 
 	if (memcmp(buf, OPREGION_SIGNATURE, 16)) {
 		DRM_DEBUG_DRIVER("opregion signature mismatch\n");
@@ -936,7 +935,7 @@ int intel_opregion_setup(struct drm_device *dev)
 
 	opregion->lid_state = base + ACPI_CLID;
 
-	mboxes = ioread32(&opregion->header->mboxes);
+	mboxes = opregion->header->mboxes;
 	if (mboxes & MBOX_ACPI) {
 		DRM_DEBUG_DRIVER("Public ACPI methods supported\n");
 		opregion->acpi = base + OPREGION_ACPI_OFFSET;
@@ -951,12 +950,12 @@ int intel_opregion_setup(struct drm_device *dev)
 		DRM_DEBUG_DRIVER("ASLE supported\n");
 		opregion->asle = base + OPREGION_ASLE_OFFSET;
 
-		iowrite32(ASLE_ARDY_NOT_READY, &opregion->asle->ardy);
+		opregion->asle->ardy = ASLE_ARDY_NOT_READY;
 	}
 
 	return 0;
 
 err_out:
-	iounmap(base);
+	memunmap(base);
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index f30c996e882c..b05c6d9b3be7 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -381,7 +381,7 @@ intel_panel_detect(struct drm_device *dev)
 
 	/* Assume that the BIOS does not lie through the OpRegion... */
 	if (!i915.panel_ignore_lid && dev_priv->opregion.lid_state) {
-		return ioread32(dev_priv->opregion.lid_state) & 0x1 ?
+		return *dev_priv->opregion.lid_state & 0x1 ?
 			connector_status_connected :
 			connector_status_disconnected;
 	}
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index d031d74abd27..9dda3eaebd12 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -52,56 +52,10 @@
 #define INTEL_RC6p_ENABLE			(1<<1)
 #define INTEL_RC6pp_ENABLE			(1<<2)
 
-static void gen9_init_clock_gating(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	/* WaEnableLbsSlaRetryTimerDecrement:skl */
-	I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) |
-		   GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE);
-
-	/* WaDisableKillLogic:bxt,skl */
-	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
-		   ECOCHK_DIS_TLB);
-}
-
-static void skl_init_clock_gating(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	gen9_init_clock_gating(dev);
-
-	if (INTEL_REVID(dev) <= SKL_REVID_D0) {
-		/* WaDisableHDCInvalidation:skl */
-		I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
-			   BDW_DISABLE_HDC_INVALIDATION);
-
-		/* WaDisableChickenBitTSGBarrierAckForFFSliceCS:skl */
-		I915_WRITE(FF_SLICE_CS_CHICKEN2,
-			   _MASKED_BIT_ENABLE(GEN9_TSG_BARRIER_ACK_DISABLE));
-	}
-
-	/* GEN8_L3SQCREG4 has a dependency with WA batch so any new changes
-	 * involving this register should also be added to WA batch as required.
-	 */
-	if (INTEL_REVID(dev) <= SKL_REVID_E0)
-		/* WaDisableLSQCROPERFforOCL:skl */
-		I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) |
-			   GEN8_LQSC_RO_PERF_DIS);
-
-	/* WaEnableGapsTsvCreditFix:skl */
-	if (IS_SKYLAKE(dev) && (INTEL_REVID(dev) >= SKL_REVID_C0)) {
-		I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) |
-					   GEN9_GAPS_TSV_CREDIT_DISABLE));
-	}
-}
-
 static void bxt_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	gen9_init_clock_gating(dev);
-
 	/* WaDisableSDEUnitClockGating:bxt */
 	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
 		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
@@ -112,17 +66,6 @@ static void bxt_init_clock_gating(struct drm_device *dev)
 	 */
 	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
 		   GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ);
-
-	/* WaStoreMultiplePTEenable:bxt */
-	/* This is a requirement according to Hardware specification */
-	if (INTEL_REVID(dev) == BXT_REVID_A0)
-		I915_WRITE(TILECTL, I915_READ(TILECTL) | TILECTL_TLBPF);
-
-	/* WaSetClckGatingDisableMedia:bxt */
-	if (INTEL_REVID(dev) == BXT_REVID_A0) {
-		I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) &
-					    ~GEN8_DOP_CLOCK_GATE_MEDIA_ENABLE));
-	}
 }
 
 static void i915_pineview_get_mem_freq(struct drm_device *dev)
@@ -1765,6 +1708,13 @@ static uint32_t ilk_wm_fbc(uint32_t pri_val, uint32_t horiz_pixels,
 	return DIV_ROUND_UP(pri_val * 64, horiz_pixels * bytes_per_pixel) + 2;
 }
 
+struct skl_pipe_wm_parameters {
+	bool active;
+	uint32_t pipe_htotal;
+	uint32_t pixel_rate; /* in KHz */
+	struct intel_plane_wm_parameters plane[I915_MAX_PLANES];
+};
+
 struct ilk_wm_maximums {
 	uint16_t pri;
 	uint16_t spr;
@@ -2805,40 +2755,18 @@ static bool ilk_disable_lp_wm(struct drm_device *dev)
 #define SKL_DDB_SIZE		896	/* in blocks */
 #define BXT_DDB_SIZE		512
 
-/*
- * Return the index of a plane in the SKL DDB and wm result arrays.  Primary
- * plane is always in slot 0, cursor is always in slot I915_MAX_PLANES-1, and
- * other universal planes are in indices 1..n.  Note that this may leave unused
- * indices between the top "sprite" plane and the cursor.
- */
-static int
-skl_wm_plane_id(const struct intel_plane *plane)
-{
-	switch (plane->base.type) {
-	case DRM_PLANE_TYPE_PRIMARY:
-		return 0;
-	case DRM_PLANE_TYPE_CURSOR:
-		return PLANE_CURSOR;
-	case DRM_PLANE_TYPE_OVERLAY:
-		return plane->plane + 1;
-	default:
-		MISSING_CASE(plane->base.type);
-		return plane->plane;
-	}
-}
-
 static void
 skl_ddb_get_pipe_allocation_limits(struct drm_device *dev,
-				   const struct intel_crtc_state *cstate,
+				   struct drm_crtc *for_crtc,
 				   const struct intel_wm_config *config,
+				   const struct skl_pipe_wm_parameters *params,
 				   struct skl_ddb_entry *alloc /* out */)
 {
-	struct drm_crtc *for_crtc = cstate->base.crtc;
 	struct drm_crtc *crtc;
 	unsigned int pipe_size, ddb_size;
 	int nth_active_pipe;
 
-	if (!cstate->base.active) {
+	if (!params->active) {
 		alloc->start = 0;
 		alloc->end = 0;
 		return;
@@ -2904,29 +2832,19 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
 }
 
 static unsigned int
-skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
-			     const struct drm_plane_state *pstate,
-			     int y)
+skl_plane_relative_data_rate(const struct intel_plane_wm_parameters *p, int y)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
-	struct drm_framebuffer *fb = pstate->fb;
 
 	/* for planar format */
-	if (fb->pixel_format == DRM_FORMAT_NV12) {
+	if (p->y_bytes_per_pixel) {
 		if (y)  /* y-plane data rate */
-			return intel_crtc->config->pipe_src_w *
-				intel_crtc->config->pipe_src_h *
-				drm_format_plane_cpp(fb->pixel_format, 0);
+			return p->horiz_pixels * p->vert_pixels * p->y_bytes_per_pixel;
 		else    /* uv-plane data rate */
-			return (intel_crtc->config->pipe_src_w/2) *
-				(intel_crtc->config->pipe_src_h/2) *
-				drm_format_plane_cpp(fb->pixel_format, 1);
+			return (p->horiz_pixels/2) * (p->vert_pixels/2) * p->bytes_per_pixel;
 	}
 
 	/* for packed formats */
-	return intel_crtc->config->pipe_src_w *
-		intel_crtc->config->pipe_src_h *
-		drm_format_plane_cpp(fb->pixel_format, 0);
+	return p->horiz_pixels * p->vert_pixels * p->bytes_per_pixel;
 }
 
 /*
@@ -2935,51 +2853,46 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
  *   3 * 4096 * 8192  * 4 < 2^32
  */
 static unsigned int
-skl_get_total_relative_data_rate(const struct intel_crtc_state *cstate)
+skl_get_total_relative_data_rate(struct intel_crtc *intel_crtc,
+				 const struct skl_pipe_wm_parameters *params)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
-	struct drm_device *dev = intel_crtc->base.dev;
-	const struct intel_plane *intel_plane;
 	unsigned int total_data_rate = 0;
+	int plane;
 
-	for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
-		const struct drm_plane_state *pstate = intel_plane->base.state;
+	for (plane = 0; plane < intel_num_planes(intel_crtc); plane++) {
+		const struct intel_plane_wm_parameters *p;
 
-		if (pstate->fb == NULL)
+		p = &params->plane[plane];
+		if (!p->enabled)
 			continue;
 
-		/* packed/uv */
-		total_data_rate += skl_plane_relative_data_rate(cstate,
-								pstate,
-								0);
-
-		if (pstate->fb->pixel_format == DRM_FORMAT_NV12)
-			/* y-plane */
-			total_data_rate += skl_plane_relative_data_rate(cstate,
-									pstate,
-									1);
+		total_data_rate += skl_plane_relative_data_rate(p, 0); /* packed/uv */
+		if (p->y_bytes_per_pixel) {
+			total_data_rate += skl_plane_relative_data_rate(p, 1); /* y-plane */
+		}
 	}
 
 	return total_data_rate;
 }
 
 static void
-skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
+skl_allocate_pipe_ddb(struct drm_crtc *crtc,
 		      const struct intel_wm_config *config,
+		      const struct skl_pipe_wm_parameters *params,
 		      struct skl_ddb_allocation *ddb /* out */)
 {
-	struct drm_crtc *crtc = cstate->base.crtc;
 	struct drm_device *dev = crtc->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct intel_plane *intel_plane;
 	enum pipe pipe = intel_crtc->pipe;
 	struct skl_ddb_entry *alloc = &ddb->pipe[pipe];
 	uint16_t alloc_size, start, cursor_blocks;
 	uint16_t minimum[I915_MAX_PLANES];
 	uint16_t y_minimum[I915_MAX_PLANES];
 	unsigned int total_data_rate;
+	int plane;
 
-	skl_ddb_get_pipe_allocation_limits(dev, cstate, config, alloc);
+	skl_ddb_get_pipe_allocation_limits(dev, crtc, config, params, alloc);
 	alloc_size = skl_ddb_entry_size(alloc);
 	if (alloc_size == 0) {
 		memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe]));
@@ -2996,20 +2909,17 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 	alloc->end -= cursor_blocks;
 
 	/* 1. Allocate the mininum required blocks for each active plane */
-	for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
-		struct drm_plane *plane = &intel_plane->base;
-		struct drm_framebuffer *fb = plane->fb;
-		int id = skl_wm_plane_id(intel_plane);
+	for_each_plane(dev_priv, pipe, plane) {
+		const struct intel_plane_wm_parameters *p;
 
-		if (fb == NULL)
-			continue;
-		if (plane->type == DRM_PLANE_TYPE_CURSOR)
+		p = &params->plane[plane];
+		if (!p->enabled)
 			continue;
 
-		minimum[id] = 8;
-		alloc_size -= minimum[id];
-		y_minimum[id] = (fb->pixel_format == DRM_FORMAT_NV12) ? 8 : 0;
-		alloc_size -= y_minimum[id];
+		minimum[plane] = 8;
+		alloc_size -= minimum[plane];
+		y_minimum[plane] = p->y_bytes_per_pixel ? 8 : 0;
+		alloc_size -= y_minimum[plane];
 	}
 
 	/*
@@ -3018,50 +2928,45 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 	 *
 	 * FIXME: we may not allocate every single block here.
 	 */
-	total_data_rate = skl_get_total_relative_data_rate(cstate);
+	total_data_rate = skl_get_total_relative_data_rate(intel_crtc, params);
 
 	start = alloc->start;
-	for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
-		struct drm_plane *plane = &intel_plane->base;
-		struct drm_plane_state *pstate = intel_plane->base.state;
+	for (plane = 0; plane < intel_num_planes(intel_crtc); plane++) {
+		const struct intel_plane_wm_parameters *p;
 		unsigned int data_rate, y_data_rate;
 		uint16_t plane_blocks, y_plane_blocks = 0;
-		int id = skl_wm_plane_id(intel_plane);
 
-		if (pstate->fb == NULL)
-			continue;
-		if (plane->type == DRM_PLANE_TYPE_CURSOR)
+		p = &params->plane[plane];
+		if (!p->enabled)
 			continue;
 
-		data_rate = skl_plane_relative_data_rate(cstate, pstate, 0);
+		data_rate = skl_plane_relative_data_rate(p, 0);
 
 		/*
 		 * allocation for (packed formats) or (uv-plane part of planar format):
 		 * promote the expression to 64 bits to avoid overflowing, the
 		 * result is < available as data_rate / total_data_rate < 1
 		 */
-		plane_blocks = minimum[id];
+		plane_blocks = minimum[plane];
 		plane_blocks += div_u64((uint64_t)alloc_size * data_rate,
 					total_data_rate);
 
-		ddb->plane[pipe][id].start = start;
-		ddb->plane[pipe][id].end = start + plane_blocks;
+		ddb->plane[pipe][plane].start = start;
+		ddb->plane[pipe][plane].end = start + plane_blocks;
 
 		start += plane_blocks;
 
 		/*
 		 * allocation for y_plane part of planar format:
 		 */
-		if (pstate->fb->pixel_format == DRM_FORMAT_NV12) {
-			y_data_rate = skl_plane_relative_data_rate(cstate,
-								   pstate,
-								   1);
-			y_plane_blocks = y_minimum[id];
+		if (p->y_bytes_per_pixel) {
+			y_data_rate = skl_plane_relative_data_rate(p, 1);
+			y_plane_blocks = y_minimum[plane];
 			y_plane_blocks += div_u64((uint64_t)alloc_size * y_data_rate,
 						total_data_rate);
 
-			ddb->y_plane[pipe][id].start = start;
-			ddb->y_plane[pipe][id].end = start + y_plane_blocks;
+			ddb->y_plane[pipe][plane].start = start;
+			ddb->y_plane[pipe][plane].end = start + y_plane_blocks;
 
 			start += y_plane_blocks;
 		}
@@ -3148,21 +3053,87 @@ static void skl_compute_wm_global_parameters(struct drm_device *dev,
 					     struct intel_wm_config *config)
 {
 	struct drm_crtc *crtc;
+	struct drm_plane *plane;
 
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
 		config->num_pipes_active += to_intel_crtc(crtc)->active;
+
+	/* FIXME: I don't think we need those two global parameters on SKL */
+	list_for_each_entry(plane, &dev->mode_config.plane_list, head) {
+		struct intel_plane *intel_plane = to_intel_plane(plane);
+
+		config->sprites_enabled |= intel_plane->wm.enabled;
+		config->sprites_scaled |= intel_plane->wm.scaled;
+	}
+}
+
+static void skl_compute_wm_pipe_parameters(struct drm_crtc *crtc,
+					   struct skl_pipe_wm_parameters *p)
+{
+	struct drm_device *dev = crtc->dev;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	enum pipe pipe = intel_crtc->pipe;
+	struct drm_plane *plane;
+	struct drm_framebuffer *fb;
+	int i = 1; /* Index for sprite planes start */
+
+	p->active = intel_crtc->active;
+	if (p->active) {
+		p->pipe_htotal = intel_crtc->config->base.adjusted_mode.crtc_htotal;
+		p->pixel_rate = skl_pipe_pixel_rate(intel_crtc->config);
+
+		fb = crtc->primary->state->fb;
+		/* For planar: Bpp is for uv plane, y_Bpp is for y plane */
+		if (fb) {
+			p->plane[0].enabled = true;
+			p->plane[0].bytes_per_pixel = fb->pixel_format == DRM_FORMAT_NV12 ?
+				drm_format_plane_cpp(fb->pixel_format, 1) :
+				drm_format_plane_cpp(fb->pixel_format, 0);
+			p->plane[0].y_bytes_per_pixel = fb->pixel_format == DRM_FORMAT_NV12 ?
+				drm_format_plane_cpp(fb->pixel_format, 0) : 0;
+			p->plane[0].tiling = fb->modifier[0];
+		} else {
+			p->plane[0].enabled = false;
+			p->plane[0].bytes_per_pixel = 0;
+			p->plane[0].y_bytes_per_pixel = 0;
+			p->plane[0].tiling = DRM_FORMAT_MOD_NONE;
+		}
+		p->plane[0].horiz_pixels = intel_crtc->config->pipe_src_w;
+		p->plane[0].vert_pixels = intel_crtc->config->pipe_src_h;
+		p->plane[0].rotation = crtc->primary->state->rotation;
+
+		fb = crtc->cursor->state->fb;
+		p->plane[PLANE_CURSOR].y_bytes_per_pixel = 0;
+		if (fb) {
+			p->plane[PLANE_CURSOR].enabled = true;
+			p->plane[PLANE_CURSOR].bytes_per_pixel = fb->bits_per_pixel / 8;
+			p->plane[PLANE_CURSOR].horiz_pixels = crtc->cursor->state->crtc_w;
+			p->plane[PLANE_CURSOR].vert_pixels = crtc->cursor->state->crtc_h;
+		} else {
+			p->plane[PLANE_CURSOR].enabled = false;
+			p->plane[PLANE_CURSOR].bytes_per_pixel = 0;
+			p->plane[PLANE_CURSOR].horiz_pixels = 64;
+			p->plane[PLANE_CURSOR].vert_pixels = 64;
+		}
+	}
+
+	list_for_each_entry(plane, &dev->mode_config.plane_list, head) {
+		struct intel_plane *intel_plane = to_intel_plane(plane);
+
+		if (intel_plane->pipe == pipe &&
+			plane->type == DRM_PLANE_TYPE_OVERLAY)
+			p->plane[i++] = intel_plane->wm;
+	}
 }
 
 static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
-				 struct intel_crtc_state *cstate,
-				 struct intel_plane *intel_plane,
+				 struct skl_pipe_wm_parameters *p,
+				 struct intel_plane_wm_parameters *p_params,
 				 uint16_t ddb_allocation,
 				 int level,
 				 uint16_t *out_blocks, /* out */
 				 uint8_t *out_lines /* out */)
 {
-	struct drm_plane *plane = &intel_plane->base;
-	struct drm_framebuffer *fb = plane->state->fb;
 	uint32_t latency = dev_priv->wm.skl_latency[level];
 	uint32_t method1, method2;
 	uint32_t plane_bytes_per_line, plane_blocks_per_line;
@@ -3170,35 +3141,31 @@ static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 	uint32_t selected_result;
 	uint8_t bytes_per_pixel;
 
-	if (latency == 0 || !cstate->base.active || !fb)
+	if (latency == 0 || !p->active || !p_params->enabled)
 		return false;
 
-	bytes_per_pixel = (fb->pixel_format == DRM_FORMAT_NV12) ?
-		drm_format_plane_cpp(DRM_FORMAT_NV12, 0) :
-		drm_format_plane_cpp(DRM_FORMAT_NV12, 1);
-	method1 = skl_wm_method1(skl_pipe_pixel_rate(cstate),
+	bytes_per_pixel = p_params->y_bytes_per_pixel ?
+		p_params->y_bytes_per_pixel :
+		p_params->bytes_per_pixel;
+	method1 = skl_wm_method1(p->pixel_rate,
 				 bytes_per_pixel,
 				 latency);
-	method2 = skl_wm_method2(skl_pipe_pixel_rate(cstate),
-				 cstate->base.adjusted_mode.crtc_htotal,
-				 cstate->pipe_src_w,
+	method2 = skl_wm_method2(p->pixel_rate,
+				 p->pipe_htotal,
+				 p_params->horiz_pixels,
 				 bytes_per_pixel,
-				 fb->modifier[0],
+				 p_params->tiling,
 				 latency);
 
-	plane_bytes_per_line = cstate->pipe_src_w * bytes_per_pixel;
+	plane_bytes_per_line = p_params->horiz_pixels * bytes_per_pixel;
 	plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512);
 
-	if (fb->modifier[0] == I915_FORMAT_MOD_Y_TILED ||
-	    fb->modifier[0] == I915_FORMAT_MOD_Yf_TILED) {
+	if (p_params->tiling == I915_FORMAT_MOD_Y_TILED ||
+	    p_params->tiling == I915_FORMAT_MOD_Yf_TILED) {
 		uint32_t min_scanlines = 4;
 		uint32_t y_tile_minimum;
-		if (intel_rotation_90_or_270(plane->state->rotation)) {
-			int bpp = (fb->pixel_format == DRM_FORMAT_NV12) ?
-				drm_format_plane_cpp(fb->pixel_format, 1) :
-				drm_format_plane_cpp(fb->pixel_format, 0);
-
-			switch (bpp) {
+		if (intel_rotation_90_or_270(p_params->rotation)) {
+			switch (p_params->bytes_per_pixel) {
 			case 1:
 				min_scanlines = 16;
 				break;
@@ -3222,8 +3189,8 @@ static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 	res_lines = DIV_ROUND_UP(selected_result, plane_blocks_per_line);
 
 	if (level >= 1 && level <= 7) {
-		if (fb->modifier[0] == I915_FORMAT_MOD_Y_TILED ||
-		    fb->modifier[0] == I915_FORMAT_MOD_Yf_TILED)
+		if (p_params->tiling == I915_FORMAT_MOD_Y_TILED ||
+		    p_params->tiling == I915_FORMAT_MOD_Yf_TILED)
 			res_lines += 4;
 		else
 			res_blocks++;
@@ -3240,80 +3207,84 @@ static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 
 static void skl_compute_wm_level(const struct drm_i915_private *dev_priv,
 				 struct skl_ddb_allocation *ddb,
-				 struct intel_crtc_state *cstate,
+				 struct skl_pipe_wm_parameters *p,
+				 enum pipe pipe,
 				 int level,
+				 int num_planes,
 				 struct skl_wm_level *result)
 {
-	struct drm_device *dev = dev_priv->dev;
-	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
-	struct intel_plane *intel_plane;
 	uint16_t ddb_blocks;
-	enum pipe pipe = intel_crtc->pipe;
-
-	for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
-		int i = skl_wm_plane_id(intel_plane);
+	int i;
 
+	for (i = 0; i < num_planes; i++) {
 		ddb_blocks = skl_ddb_entry_size(&ddb->plane[pipe][i]);
 
 		result->plane_en[i] = skl_compute_plane_wm(dev_priv,
-						cstate,
-						intel_plane,
+						p, &p->plane[i],
 						ddb_blocks,
 						level,
 						&result->plane_res_b[i],
 						&result->plane_res_l[i]);
 	}
+
+	ddb_blocks = skl_ddb_entry_size(&ddb->plane[pipe][PLANE_CURSOR]);
+	result->plane_en[PLANE_CURSOR] = skl_compute_plane_wm(dev_priv, p,
+						 &p->plane[PLANE_CURSOR],
+						 ddb_blocks, level,
+						 &result->plane_res_b[PLANE_CURSOR],
+						 &result->plane_res_l[PLANE_CURSOR]);
 }
 
 static uint32_t
-skl_compute_linetime_wm(struct intel_crtc_state *cstate)
+skl_compute_linetime_wm(struct drm_crtc *crtc, struct skl_pipe_wm_parameters *p)
 {
-	if (!cstate->base.active)
+	if (!to_intel_crtc(crtc)->active)
 		return 0;
 
-	if (WARN_ON(skl_pipe_pixel_rate(cstate) == 0))
+	if (WARN_ON(p->pixel_rate == 0))
 		return 0;
 
-	return DIV_ROUND_UP(8 * cstate->base.adjusted_mode.crtc_htotal * 1000,
-			    skl_pipe_pixel_rate(cstate));
+	return DIV_ROUND_UP(8 * p->pipe_htotal * 1000, p->pixel_rate);
 }
 
-static void skl_compute_transition_wm(struct intel_crtc_state *cstate,
+static void skl_compute_transition_wm(struct drm_crtc *crtc,
+				      struct skl_pipe_wm_parameters *params,
 				      struct skl_wm_level *trans_wm /* out */)
 {
-	struct drm_crtc *crtc = cstate->base.crtc;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct intel_plane *intel_plane;
+	int i;
 
-	if (!cstate->base.active)
+	if (!params->active)
 		return;
 
 	/* Until we know more, just disable transition WMs */
-	for_each_intel_plane_on_crtc(crtc->dev, intel_crtc, intel_plane) {
-		int i = skl_wm_plane_id(intel_plane);
-
+	for (i = 0; i < intel_num_planes(intel_crtc); i++)
 		trans_wm->plane_en[i] = false;
-	}
+	trans_wm->plane_en[PLANE_CURSOR] = false;
 }
 
-static void skl_compute_pipe_wm(struct intel_crtc_state *cstate,
+static void skl_compute_pipe_wm(struct drm_crtc *crtc,
 				struct skl_ddb_allocation *ddb,
+				struct skl_pipe_wm_parameters *params,
 				struct skl_pipe_wm *pipe_wm)
 {
-	struct drm_device *dev = cstate->base.crtc->dev;
+	struct drm_device *dev = crtc->dev;
 	const struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int level, max_level = ilk_wm_max_level(dev);
 
 	for (level = 0; level <= max_level; level++) {
-		skl_compute_wm_level(dev_priv, ddb, cstate,
-				     level, &pipe_wm->wm[level]);
+		skl_compute_wm_level(dev_priv, ddb, params, intel_crtc->pipe,
+				     level, intel_num_planes(intel_crtc),
+				     &pipe_wm->wm[level]);
 	}
-	pipe_wm->linetime = skl_compute_linetime_wm(cstate);
+	pipe_wm->linetime = skl_compute_linetime_wm(crtc, params);
 
-	skl_compute_transition_wm(cstate, &pipe_wm->trans_wm);
+	skl_compute_transition_wm(crtc, params, &pipe_wm->trans_wm);
 }
 
 static void skl_compute_wm_results(struct drm_device *dev,
+				   struct skl_pipe_wm_parameters *p,
 				   struct skl_pipe_wm *p_wm,
 				   struct skl_wm_values *r,
 				   struct intel_crtc *intel_crtc)
@@ -3557,15 +3528,16 @@ static void skl_flush_wm_values(struct drm_i915_private *dev_priv,
 }
 
 static bool skl_update_pipe_wm(struct drm_crtc *crtc,
+			       struct skl_pipe_wm_parameters *params,
 			       struct intel_wm_config *config,
 			       struct skl_ddb_allocation *ddb, /* out */
 			       struct skl_pipe_wm *pipe_wm /* out */)
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state);
 
-	skl_allocate_pipe_ddb(cstate, config, ddb);
-	skl_compute_pipe_wm(cstate, ddb, pipe_wm);
+	skl_compute_wm_pipe_parameters(crtc, params);
+	skl_allocate_pipe_ddb(crtc, config, params, ddb);
+	skl_compute_pipe_wm(crtc, ddb, params, pipe_wm);
 
 	if (!memcmp(&intel_crtc->wm.skl_active, pipe_wm, sizeof(*pipe_wm)))
 		return false;
@@ -3598,6 +3570,7 @@ static void skl_update_other_pipe_wm(struct drm_device *dev,
 	 */
 	list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list,
 				base.head) {
+		struct skl_pipe_wm_parameters params = {};
 		struct skl_pipe_wm pipe_wm = {};
 		bool wm_changed;
 
@@ -3607,7 +3580,8 @@ static void skl_update_other_pipe_wm(struct drm_device *dev,
 		if (!intel_crtc->active)
 			continue;
 
-		wm_changed = skl_update_pipe_wm(&intel_crtc->base, config,
+		wm_changed = skl_update_pipe_wm(&intel_crtc->base,
+						&params, config,
 						&r->ddb, &pipe_wm);
 
 		/*
@@ -3617,7 +3591,7 @@ static void skl_update_other_pipe_wm(struct drm_device *dev,
 		 */
 		WARN_ON(!wm_changed);
 
-		skl_compute_wm_results(dev, &pipe_wm, r, intel_crtc);
+		skl_compute_wm_results(dev, &params, &pipe_wm, r, intel_crtc);
 		r->dirty[intel_crtc->pipe] = true;
 	}
 }
@@ -3647,6 +3621,7 @@ static void skl_update_wm(struct drm_crtc *crtc)
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct skl_pipe_wm_parameters params = {};
 	struct skl_wm_values *results = &dev_priv->wm.skl_results;
 	struct skl_pipe_wm pipe_wm = {};
 	struct intel_wm_config config = {};
@@ -3659,10 +3634,11 @@ static void skl_update_wm(struct drm_crtc *crtc)
 
 	skl_compute_wm_global_parameters(dev, &config);
 
-	if (!skl_update_pipe_wm(crtc, &config, &results->ddb, &pipe_wm))
+	if (!skl_update_pipe_wm(crtc, &params, &config,
+				&results->ddb, &pipe_wm))
 		return;
 
-	skl_compute_wm_results(dev, &pipe_wm, results, intel_crtc);
+	skl_compute_wm_results(dev, &params, &pipe_wm, results, intel_crtc);
 	results->dirty[intel_crtc->pipe] = true;
 
 	skl_update_other_pipe_wm(dev, crtc, &config, results);
@@ -3673,6 +3649,39 @@ static void skl_update_wm(struct drm_crtc *crtc)
 	dev_priv->wm.skl_hw = *results;
 }
 
+static void
+skl_update_sprite_wm(struct drm_plane *plane, struct drm_crtc *crtc,
+		     uint32_t sprite_width, uint32_t sprite_height,
+		     int pixel_size, bool enabled, bool scaled)
+{
+	struct intel_plane *intel_plane = to_intel_plane(plane);
+	struct drm_framebuffer *fb = plane->state->fb;
+
+	intel_plane->wm.enabled = enabled;
+	intel_plane->wm.scaled = scaled;
+	intel_plane->wm.horiz_pixels = sprite_width;
+	intel_plane->wm.vert_pixels = sprite_height;
+	intel_plane->wm.tiling = DRM_FORMAT_MOD_NONE;
+
+	/* For planar: Bpp is for UV plane, y_Bpp is for Y plane */
+	intel_plane->wm.bytes_per_pixel =
+		(fb && fb->pixel_format == DRM_FORMAT_NV12) ?
+		drm_format_plane_cpp(plane->state->fb->pixel_format, 1) : pixel_size;
+	intel_plane->wm.y_bytes_per_pixel =
+		(fb && fb->pixel_format == DRM_FORMAT_NV12) ?
+		drm_format_plane_cpp(plane->state->fb->pixel_format, 0) : 0;
+
+	/*
+	 * Framebuffer can be NULL on plane disable, but it does not
+	 * matter for watermarks if we assume no tiling in that case.
+	 */
+	if (fb)
+		intel_plane->wm.tiling = fb->modifier[0];
+	intel_plane->wm.rotation = plane->state->rotation;
+
+	skl_update_wm(crtc);
+}
+
 static void ilk_update_wm(struct drm_crtc *crtc)
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
@@ -3688,18 +3697,6 @@ static void ilk_update_wm(struct drm_crtc *crtc)
 
 	WARN_ON(cstate->base.active != intel_crtc->active);
 
-	/*
-	 * IVB workaround: must disable low power watermarks for at least
-	 * one frame before enabling scaling.  LP watermarks can be re-enabled
-	 * when scaling is disabled.
-	 *
-	 * WaCxSRDisabledForSpriteScaling:ivb
-	 */
-	if (cstate->disable_lp_wm) {
-		ilk_disable_lp_wm(dev);
-		intel_wait_for_vblank(dev, intel_crtc->pipe);
-	}
-
 	intel_compute_pipe_wm(cstate, &pipe_wm);
 
 	if (!memcmp(&intel_crtc->wm.active, &pipe_wm, sizeof(pipe_wm)))
@@ -3731,6 +3728,28 @@ static void ilk_update_wm(struct drm_crtc *crtc)
 	ilk_write_wm_values(dev_priv, &results);
 }
 
+static void
+ilk_update_sprite_wm(struct drm_plane *plane,
+		     struct drm_crtc *crtc,
+		     uint32_t sprite_width, uint32_t sprite_height,
+		     int pixel_size, bool enabled, bool scaled)
+{
+	struct drm_device *dev = plane->dev;
+	struct intel_plane *intel_plane = to_intel_plane(plane);
+
+	/*
+	 * IVB workaround: must disable low power watermarks for at least
+	 * one frame before enabling scaling.  LP watermarks can be re-enabled
+	 * when scaling is disabled.
+	 *
+	 * WaCxSRDisabledForSpriteScaling:ivb
+	 */
+	if (IS_IVYBRIDGE(dev) && scaled && ilk_disable_lp_wm(dev))
+		intel_wait_for_vblank(dev, intel_plane->pipe);
+
+	ilk_update_wm(crtc);
+}
+
 static void skl_pipe_wm_active_state(uint32_t val,
 				     struct skl_pipe_wm *active,
 				     bool is_transwm,
@@ -4108,6 +4127,21 @@ void intel_update_watermarks(struct drm_crtc *crtc)
 		dev_priv->display.update_wm(crtc);
 }
 
+void intel_update_sprite_watermarks(struct drm_plane *plane,
+				    struct drm_crtc *crtc,
+				    uint32_t sprite_width,
+				    uint32_t sprite_height,
+				    int pixel_size,
+				    bool enabled, bool scaled)
+{
+	struct drm_i915_private *dev_priv = plane->dev->dev_private;
+
+	if (dev_priv->display.update_sprite_wm)
+		dev_priv->display.update_sprite_wm(plane, crtc,
+						   sprite_width, sprite_height,
+						   pixel_size, enabled, scaled);
+}
+
 /**
  * Lock protecting IPS related data structures
  */
@@ -7018,10 +7052,8 @@ void intel_init_pm(struct drm_device *dev)
 		if (IS_BROXTON(dev))
 			dev_priv->display.init_clock_gating =
 				bxt_init_clock_gating;
-		else if (IS_SKYLAKE(dev))
-			dev_priv->display.init_clock_gating =
-				skl_init_clock_gating;
 		dev_priv->display.update_wm = skl_update_wm;
+		dev_priv->display.update_sprite_wm = skl_update_sprite_wm;
 	} else if (HAS_PCH_SPLIT(dev)) {
 		ilk_setup_wm_latency(dev);
 
@@ -7030,6 +7062,7 @@ void intel_init_pm(struct drm_device *dev)
 		    (!IS_GEN5(dev) && dev_priv->wm.pri_latency[0] &&
 		     dev_priv->wm.spr_latency[0] && dev_priv->wm.cur_latency[0])) {
 			dev_priv->display.update_wm = ilk_update_wm;
+			dev_priv->display.update_sprite_wm = ilk_update_sprite_wm;
 		} else {
 			DRM_DEBUG_KMS("Failed to read display plane latency. "
 				      "Disable CxSR\n");
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index a04b4dc5ed9b..213581c215b3 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -73,14 +73,14 @@ static bool vlv_is_psr_active_on_pipe(struct drm_device *dev, int pipe)
 }
 
 static void intel_psr_write_vsc(struct intel_dp *intel_dp,
-				    struct edp_vsc_psr *vsc_psr)
+				const struct edp_vsc_psr *vsc_psr)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *crtc = to_intel_crtc(dig_port->base.base.crtc);
-	u32 ctl_reg = HSW_TVIDEO_DIP_CTL(crtc->config->cpu_transcoder);
-	u32 data_reg = HSW_TVIDEO_DIP_VSC_DATA(crtc->config->cpu_transcoder);
+	enum transcoder cpu_transcoder = crtc->config->cpu_transcoder;
+	u32 ctl_reg = HSW_TVIDEO_DIP_CTL(cpu_transcoder);
 	uint32_t *data = (uint32_t *) vsc_psr;
 	unsigned int i;
 
@@ -90,12 +90,14 @@ static void intel_psr_write_vsc(struct intel_dp *intel_dp,
 	I915_WRITE(ctl_reg, 0);
 	POSTING_READ(ctl_reg);
 
-	for (i = 0; i < VIDEO_DIP_VSC_DATA_SIZE; i += 4) {
-		if (i < sizeof(struct edp_vsc_psr))
-			I915_WRITE(data_reg + i, *data++);
-		else
-			I915_WRITE(data_reg + i, 0);
+	for (i = 0; i < sizeof(*vsc_psr); i += 4) {
+		I915_WRITE(HSW_TVIDEO_DIP_VSC_DATA(cpu_transcoder,
+						   i >> 2), *data);
+		data++;
 	}
+	for (; i < VIDEO_DIP_VSC_DATA_SIZE; i += 4)
+		I915_WRITE(HSW_TVIDEO_DIP_VSC_DATA(cpu_transcoder,
+						   i >> 2), 0);
 
 	I915_WRITE(ctl_reg, VIDEO_DIP_ENABLE_VSC_HSW);
 	POSTING_READ(ctl_reg);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 654ae991ea13..0359736fe979 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -906,6 +906,14 @@ static int gen9_init_workarounds(struct intel_engine_cs *ring)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t tmp;
 
+	/* WaEnableLbsSlaRetryTimerDecrement:skl */
+	I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) |
+		   GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE);
+
+	/* WaDisableKillLogic:bxt,skl */
+	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
+		   ECOCHK_DIS_TLB);
+
 	/* WaDisablePartialInstShootdown:skl,bxt */
 	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
 			  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
@@ -1018,7 +1026,6 @@ static int skl_tune_iz_hashing(struct intel_engine_cs *ring)
 	return 0;
 }
 
-
 static int skl_init_workarounds(struct intel_engine_cs *ring)
 {
 	int ret;
@@ -1029,6 +1036,30 @@ static int skl_init_workarounds(struct intel_engine_cs *ring)
 	if (ret)
 		return ret;
 
+	if (INTEL_REVID(dev) <= SKL_REVID_D0) {
+		/* WaDisableHDCInvalidation:skl */
+		I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
+			   BDW_DISABLE_HDC_INVALIDATION);
+
+		/* WaDisableChickenBitTSGBarrierAckForFFSliceCS:skl */
+		I915_WRITE(FF_SLICE_CS_CHICKEN2,
+			   _MASKED_BIT_ENABLE(GEN9_TSG_BARRIER_ACK_DISABLE));
+	}
+
+	/* GEN8_L3SQCREG4 has a dependency with WA batch so any new changes
+	 * involving this register should also be added to WA batch as required.
+	 */
+	if (INTEL_REVID(dev) <= SKL_REVID_E0)
+		/* WaDisableLSQCROPERFforOCL:skl */
+		I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) |
+			   GEN8_LQSC_RO_PERF_DIS);
+
+	/* WaEnableGapsTsvCreditFix:skl */
+	if (IS_SKYLAKE(dev) && (INTEL_REVID(dev) >= SKL_REVID_C0)) {
+		I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) |
+					   GEN9_GAPS_TSV_CREDIT_DISABLE));
+	}
+
 	/* WaDisablePowerCompilerClockGating:skl */
 	if (INTEL_REVID(dev) == SKL_REVID_B0)
 		WA_SET_BIT_MASKED(HIZ_CHICKEN,
@@ -1072,6 +1103,17 @@ static int bxt_init_workarounds(struct intel_engine_cs *ring)
 	if (ret)
 		return ret;
 
+	/* WaStoreMultiplePTEenable:bxt */
+	/* This is a requirement according to Hardware specification */
+	if (INTEL_REVID(dev) == BXT_REVID_A0)
+		I915_WRITE(TILECTL, I915_READ(TILECTL) | TILECTL_TLBPF);
+
+	/* WaSetClckGatingDisableMedia:bxt */
+	if (INTEL_REVID(dev) == BXT_REVID_A0) {
+		I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) &
+					    ~GEN8_DOP_CLOCK_GATE_MEDIA_ENABLE));
+	}
+
 	/* WaDisableThreadStallDopClockGating:bxt */
 	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
 			  STALL_DOP_GATING_DISABLE);
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index dd2d5683fcb1..56dc132e8e20 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -192,6 +192,7 @@ skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc,
 	const int pipe = intel_plane->pipe;
 	const int plane = intel_plane->plane + 1;
 	u32 plane_ctl, stride_div, stride;
+	int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
 	const struct drm_intel_sprite_colorkey *key =
 		&to_intel_plane_state(drm_plane->state)->ckey;
 	unsigned long surf_addr;
@@ -202,6 +203,7 @@ skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc,
 	int scaler_id;
 
 	plane_ctl = PLANE_CTL_ENABLE |
+		PLANE_CTL_PIPE_GAMMA_ENABLE |
 		PLANE_CTL_PIPE_CSC_ENABLE;
 
 	plane_ctl |= skl_plane_ctl_format(fb->pixel_format);
@@ -210,6 +212,10 @@ skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc,
 	rotation = drm_plane->state->rotation;
 	plane_ctl |= skl_plane_ctl_rotation(rotation);
 
+	intel_update_sprite_watermarks(drm_plane, crtc, src_w, src_h,
+				       pixel_size, true,
+				       src_w != crtc_w || src_h != crtc_h);
+
 	stride_div = intel_fb_stride_alignment(dev, fb->modifier[0],
 					       fb->pixel_format);
 
@@ -291,6 +297,8 @@ skl_disable_plane(struct drm_plane *dplane, struct drm_crtc *crtc)
 
 	I915_WRITE(PLANE_SURF(pipe, plane), 0);
 	POSTING_READ(PLANE_SURF(pipe, plane));
+
+	intel_update_sprite_watermarks(dplane, crtc, 0, 0, 0, false, false);
 }
 
 static void
@@ -533,6 +541,10 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		sprctl |= SPRITE_PIPE_CSC_ENABLE;
 
+	intel_update_sprite_watermarks(plane, crtc, src_w, src_h, pixel_size,
+				       true,
+				       src_w != crtc_w || src_h != crtc_h);
+
 	/* Sizes are 0 based */
 	src_w--;
 	src_h--;
@@ -601,7 +613,7 @@ ivb_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc)
 	struct intel_plane *intel_plane = to_intel_plane(plane);
 	int pipe = intel_plane->pipe;
 
-	I915_WRITE(SPRCTL(pipe), I915_READ(SPRCTL(pipe)) & ~SPRITE_ENABLE);
+	I915_WRITE(SPRCTL(pipe), 0);
 	/* Can't leave the scaler enabled... */
 	if (intel_plane->can_scale)
 		I915_WRITE(SPRSCALE(pipe), 0);
@@ -666,6 +678,10 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	if (IS_GEN6(dev))
 		dvscntr |= DVS_TRICKLE_FEED_DISABLE; /* must disable */
 
+	intel_update_sprite_watermarks(plane, crtc, src_w, src_h,
+				       pixel_size, true,
+				       src_w != crtc_w || src_h != crtc_h);
+
 	/* Sizes are 0 based */
 	src_w--;
 	src_h--;
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index b43c6d025ac3..1663ea55e37c 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -525,7 +525,7 @@ void assert_forcewakes_inactive(struct drm_i915_private *dev_priv)
 }
 
 /* We give fast paths for the really cool registers */
-#define NEEDS_FORCE_WAKE(dev_priv, reg) \
+#define NEEDS_FORCE_WAKE(reg) \
 	 ((reg) < 0x40000 && (reg) != FORCEWAKE)
 
 #define REG_RANGE(reg, start, end) ((reg) >= (start) && (reg) < (end))
@@ -727,7 +727,7 @@ static u##x \
 gen6_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
 	GEN6_READ_HEADER(x); \
 	hsw_unclaimed_reg_debug(dev_priv, reg, true, true); \
-	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) \
+	if (NEEDS_FORCE_WAKE(reg)) \
 		__force_wake_get(dev_priv, FORCEWAKE_RENDER); \
 	val = __raw_i915_read##x(dev_priv, reg); \
 	hsw_unclaimed_reg_debug(dev_priv, reg, true, false); \
@@ -761,7 +761,7 @@ chv_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
 	GEN6_READ_FOOTER; \
 }
 
-#define SKL_NEEDS_FORCE_WAKE(dev_priv, reg)	\
+#define SKL_NEEDS_FORCE_WAKE(reg) \
 	 ((reg) < 0x40000 && !FORCEWAKE_GEN9_UNCORE_RANGE_OFFSET(reg))
 
 #define __gen9_read(x) \
@@ -770,9 +770,9 @@ gen9_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
 	enum forcewake_domains fw_engine; \
 	GEN6_READ_HEADER(x); \
 	hsw_unclaimed_reg_debug(dev_priv, reg, true, true); \
-	if (!SKL_NEEDS_FORCE_WAKE((dev_priv), (reg)))	\
+	if (!SKL_NEEDS_FORCE_WAKE(reg)) \
 		fw_engine = 0; \
-	else if (FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(reg))	\
+	else if (FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(reg)) \
 		fw_engine = FORCEWAKE_RENDER; \
 	else if (FORCEWAKE_GEN9_MEDIA_RANGE_OFFSET(reg)) \
 		fw_engine = FORCEWAKE_MEDIA; \
@@ -868,7 +868,7 @@ static void \
 gen6_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace) { \
 	u32 __fifo_ret = 0; \
 	GEN6_WRITE_HEADER; \
-	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
+	if (NEEDS_FORCE_WAKE(reg)) { \
 		__fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \
 	} \
 	__raw_i915_write##x(dev_priv, reg, val); \
@@ -883,7 +883,7 @@ static void \
 hsw_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace) { \
 	u32 __fifo_ret = 0; \
 	GEN6_WRITE_HEADER; \
-	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
+	if (NEEDS_FORCE_WAKE(reg)) { \
 		__fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \
 	} \
 	hsw_unclaimed_reg_debug(dev_priv, reg, false, true); \
@@ -985,7 +985,7 @@ gen9_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, \
 	enum forcewake_domains fw_engine; \
 	GEN6_WRITE_HEADER; \
 	hsw_unclaimed_reg_debug(dev_priv, reg, false, true); \
-	if (!SKL_NEEDS_FORCE_WAKE((dev_priv), (reg)) ||	\
+	if (!SKL_NEEDS_FORCE_WAKE(reg) || \
 	    is_gen9_shadowed(dev_priv, reg)) \
 		fw_engine = 0; \
 	else if (FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(reg)) \
author	Dave Airlie <airlied@redhat.com>	2015-10-30 02:45:33 +0300
committer	Dave Airlie <airlied@redhat.com>	2015-10-30 02:45:33 +0300
commit	974e59ba0bc3bcc94d11fce9b34c10af32b5930f (patch)
tree	51a970b2035018591ce0669aafc065ff20a80ee7
parent	d7e1bc3f5e70c5a106606e33cfa4d413459611ba (diff)
parent	606bb5e0b28b540685fb94c22902cd9a948a3779 (diff)
download	linux-974e59ba0bc3bcc94d11fce9b34c10af32b5930f.tar.xz